Lecture Videos

Introduction

Over the past three weeks we have had the opportunity to explore reproducible data project management strategies and analyze the patterns of social vulnerability in our Census Divisions. Specifically, we have identified the least and most vulnerable areas within our states of interest via descriptive statistics and data visualization techniques.

This week we will expand beyond this analysis to embark on a study of the relationship between our identified areas of social vulnerability and the governmental policy interventions of two tax credit programs: the New Markets Tax Credit program (NMTC), and the Low Income Housing Tax Credit program (LIHTC).

To begin, we will review videos and program summaries to gain a better understanding of the history and purpose of these credits and then conduct exploratory data analyses to determine whether there is a relationship between our identified areas of Social Vulnerability in 2010 and the amount of funds these areas received if they were eligible for either of the programs from 2011 - 2020.

We will employ a few different strategies to complete this analysis:

Correlation
K-Means Clustering
Bivariate mapping

For correlation, we will create and examine scatterplots to visualize whether our data shows a visual trend between SVI and the tax credit programs. We will also use box plots to further examine any potential outliers or influential points within our data.

Next we will calculate and interpret the Pearson Correlation Coefficient (r) to better quantify this relationship. While there is no official chart with cut-off points to determine the strength of a relationship, there are some general guidelines such as the following chart from Boston University School of Public Health, which we will utilize to interpret our analyses:

Alt-text: Boston University School of Public Health correlation score chart

Following our analysis of the correlation of all counties in our division, we will then utilize an unsupervised statistical/machine learning algorithm and its accompanying Elbow Plot to create groups/clusters within our data set that are closely related. We can then examine each of these clusters individually to see if any trends change.

Finally we will report our findings on both our SVI and tax credit programs on a specialized choropleth map known as a bivariate map.

Tax Credit Programs

New Markets Tax Credit Program

History: Created in 2000, authorized by Congress under the Community Renewal and Tax Relief Act of 2000, most recently, the Taxpayer Certainty and Disaster Tax Relief Act of 2020 provided $5 billion in NMTC Allocation authority for calendar years through 2025 (CDFI Fund, 2022). There were bills introduced in 2023 to make the NMTC program permanent (Novogradac, 2023).

Recipients: NMTCs are awarded to Community Development Entities, not to individuals or businesses. (CDFI Fund, 2022)

Purpose: make Qualified Low-Income Community Investments (QLICIs), such as business loans, in Low-Income Communities (CDFI Fund, 2022)

The NMTC program provides tax credit dollars to Community Development Entities with the intention of improving low income communities by encouraging developers to build new projects within the community that can create new jobs and provide additional services.

Tip

Eligibility criteria for the NMTC program is quite extensive:

Sites located in non-metropolitan (i.e., rural) census tracts must meet the following criteria:

Median family income: < 80%
Poverty rate: > 20%

Sites located in metropolitan areas must meet one of the primary criteria listed below or two of the secondary criteria listed below:

Primary criteria for sites located in metropolitan areas include:

Median family income: < 60%
Poverty rate: > 30%
Unemployment rate: > 1.50x the National Average

Secondary criteria for sites located in metropolitan areas include:

Poverty rate greater than 25%; median family income not exceeding 70%; or unemployment rates at least 1.25 times the national average
Federally designated Empowerment Zone, Enterprise Community or Renewal Community
SBA designated HUB Zone, when NMTC financing will support businesses that obtain HUB Zone certification by the SBA
Federal Brownfield sites as defined under 42 U.S.C. 9601 (39)
Area encompassed by a HOPE VI redevelopment plan
Native American or Alaskan Native areas, Hawaiian Homelands, or redevelopment areas by the appropriate Tribal or other authority
Areas designated as distressed by the Appalachian Regional Commission of Delta Regional Authority
Colonias areas as designated by the U.S. Department of Housing and Urban Development
Federal Opportunity Zones
Federally designated medically underserved area, when NMTC financing activities will result in the support of health-related services
State Enterprise Zone, or other similar state/local programs targeted toward economically distressed communities
Counties for which the Federal Emergency Management Agency has issued a “major disaster declaration” and made a determination that such county is eligible for both “individual and public assistance” provided that initial investment be made within 24 months of the disaster declaration
Businesses certified by the Department of Commerce as eligible for assistance under the Trade Adjustment Assistance for Firms program
Businesses located in food deserts under the Healthy Food Financing Initiative definition (USDA-ERS) to the extent NMTC financing will increase access to healthy food

Sites located in non-metropolitan (i.e., rural) census tracts must meet the following criteria:

Median family income: < 80%
Poverty rate: > 20%

Sites located in metropolitan areas must meet one of the primary criteria listed below or two of the secondary criteria listed below:

Primary criteria for sites located in metropolitan areas include:

Median family income: < 60%
Poverty rate: > 30%
Unemployment rate: > 1.50x the National Average

Secondary criteria for sites located in metropolitan areas include:

Poverty rate greater than 25%; median family income not exceeding 70%; or unemployment rates at least 1.25 times the national average
Federally designated Empowerment Zone, Enterprise Community or Renewal Community
SBA designated HUB Zone, when NMTC financing will support businesses that obtain HUB Zone certification by the SBA
Federal Brownfield sites as defined under 42 U.S.C. 9601 (39)
Area encompassed by a HOPE VI redevelopment plan
Native American or Alaskan Native areas, Hawaiian Homelands, or redevelopment areas by the appropriate Tribal or other authority
Areas designated as distressed by the Appalachian Regional Commission of Delta Regional Authority
Colonias areas as designated by the U.S. Department of Housing and Urban Development
Federal Opportunity Zones
Federally designated medically underserved area, when NMTC financing activities will result in the support of health-related services
State Enterprise Zone, or other similar state/local programs targeted toward economically distressed communities
Counties for which the Federal Emergency Management Agency has issued a “major disaster declaration” and made a determination that such county is eligible for both “individual and public assistance” provided that initial investment be made within 24 months of the disaster declaration
Businesses certified by the Department of Commerce as eligible for assistance under the Trade Adjustment Assistance for Firms program
Businesses located in food deserts under the Healthy Food Financing Initiative definition (USDA-ERS) to the extent NMTC financing will increase access to healthy food

Watch the following video for a comprehensive overview:

Low Income Housing Tax Credit Program

History: Created in 1986, authorized by Congress under the Tax Reform Act of 1986, most recent legislation to impact the LIHTC program was the Inflation Reduction Act of 2022 which increased credits/bonuses (Urban Institute, 2018; Congressional Research Service, 2023)

Recipients: Private investors (Urban Institute, 2018)

Purpose: It is “an incentive to make equity investments in affordable rental housing. The equity raised is used to construct new properties, acquire and renovate existing buildings, and refinance and renovate existing affordable rental housing properties that have previously been financed through other federal housing programs” (Urban Institute, 2018)

The LIHTC program provides tax credit dollars to private investors with the intention of increasing affordable rental housing facilities within communities.

Tip

For the LIHTC program census tracts must be deemed eligible based on one of the following criteria:

50 percent of households with incomes below 60 percent of the Area Median Gross Income (AMGI)
Poverty rate of 25 percent or more
Qualify as a Difficult Development Areas (DDA) with high land, construction, and utility costs relative to the area median income

Analysis Methodologies

Correlation

You will recall from your previous statistical and analytics courses that “correlation” refers to the statistical relationship between two variables. A positive relationship refers to two variables that trend in the same direction (example: the increasing height and weight of a puppy as he grows). While a negative relationship refers to two variables that trend in opposite directions (example: the more people who need to share a cake, the smaller the pieces will be).

Watch the video below for a more in-depth review:

K-Means Clustering

Landman et al. of Brilliant.org define K-Means Clustering in the following way:

K-means clustering is a traditional, simple machine learning algorithm that is trained on a test data set and then able to classify a new data set using a prime, k number of clusters defined a priori.

Statistician Jim Frost further explains:

The K means clustering algorithm divides a set of n observations into k clusters. … In general, clustering is a method of assigning comparable data points to groups using data patterns. Clustering algorithms find similar data points and allocate them to the same set. K means clustering is one such algorithm.

Review the following video to see this machine learning technique in action:

Bivariate Mapping

As explained on the Water Programming Blog of the Reed Research Group on Decision Analytics for Complex Systems at Cornell University:

Choropleth maps are a ubiquitous tool in geospatial analysis where color is used to visualize the spatial variability of data (e.g., coloring counties based on temperature, GDP, or election results). Bivariate choropleth maps are a less common variant that use 2-dimensional color palettes to show two different types of data at once. This can be a powerful tool for visualizing spatial correlations and clustering patterns between two related variables.

Thus we can build upon the univariate choropleth maps we explored last week to examine our correlations on a bivariate map using the R package biscale by Chris Prener

If you would like to learn more about this mapping technique ahead of creating our own maps in the lab this week, check out the following video:

Additional Readings

If you would like to explore the topics introduced above further, feel free to review the following readings and then begin this week’s lab:

Readings on NMTC and LIHTC Programs:

NMTC and LIHTC Overview: https://ds4ps.org/cpp-528-spr-2020/lectures/NMTC-and-LIHTC-overview.pdf
The Tax Policy Center’s Briefing Book, What is the New Markets Tax Credit, and how does it work? https://www.taxpolicycenter.org/briefing-book/what-new-markets-tax-credit-and-how-does-it-work
The Urban Institute (2021). The Past, Present, and Future of the New Markets Tax Credit Program https://www.urban.org/events/past-present-and-future-new-markets-tax-credit-program
The Urban Institute (2021). What Are the NMTC Program’s Impacts on Local Economic Conditions? https://www.urban.org/sites/default/files/publication/103959/what-are-the-nmtc-programs-impacts-on-local-economic-conditions_0.pdf
CDFI Fund (2020). New Markets Tax Credit Program https://www.cdfifund.gov/sites/cdfi/files/documents/nmtc-fact-sheet-english-16sept2020-final.pdf
CDFI Fund (2022). Introduction to the New Markets Tax Credit Program [https://www.cdfifund.gov/sites/cdfi/files/2022-11/CY_2022_Introduction_to_the_NMTC_Program.pdf]
Novogradac (2023). NMTC Has Record of Success and Wide Support: The Time for Permanence is Now https://www.novoco.com/periodicals/articles/nmtc-has-record-success-and-wide-support-time-permanence-now
The Tax Policy Center’s Briefing Book, What is the Low-Income Housing Tax Credit and how does it work? https://www.taxpolicycenter.org/briefing-book/what-low-income-housing-tax-credit-and-how-does-it-work
The Urban Institute (2018). The Low-Income Housing Tax Credit: How It Works and Who It Serves https://www.urban.org/sites/default/files/publication/98758/lithc_how_it_works_and_who_it_serves_final_0.pdf
Novogradac (n.d.). About the LIHTC https://www.novoco.com/resource-centers/affordable-housing-tax-credits/about-lihtc
Tax Foundation (2020). An Overview of the Low-Income Housing Tax Credit (LIHTC) https://taxfoundation.org/research/all/federal/low-income-housing-tax-credit-lihtc/
Congressional Research Service (2023). An Introduction to the Low-Income Housing Tax Credit https://sgp.fas.org/crs/misc/RS22389.pdf

Readings on Correlation and Outliers:

The Correlation Coefficient (r) https://sphweb.bumc.bu.edu/otlt/MPH-Modules/PH717-QuantCore/PH717-Module9-Correlation-Regression/PH717-Module9-Correlation-Regression4.html
Scatterplots and Correlation https://www.westga.edu/academics/research/vrc/assets/docs/scatterplots_and_correlation_notes.pdf
Outliers and Influential Points https://www.stat.cmu.edu/~larry/=stat401/lecture-20.pdf
Guidelines for Removing and Handling Outliers in Data https://statisticsbyjim.com/basics/remove-outliers/
Influential Points https://online.stat.psu.edu/stat462/node/174/
Independent and Dependent Variables https://nces.ed.gov/nceskids/help/user_guide/graph/variables.asp
Statistical Graphing https://www2.nau.edu/lrm22/lessons/graph_tips/graph_tips.html#:~:text=The%20Axes,%2Daxis%20(vertical%20line)

Readings on K-Means Clustering:

K-means Cluster Analysis https://uc-r.github.io/kmeans_clustering
What is K Means Clustering? With an Example https://statisticsbyjim.com/basics/k-means-clustering/
K-Means Clustering in R Tutorial https://www.datacamp.com/tutorial/k-means-clustering-r

Readings on Bivariate Mapping and the biscale and cowplot Packages:

Bivariate Choropleth Maps: A How-to Guide https://www.joshuastevens.net/cartography/make-a-bivariate-choropleth-map/
biscale R package https://chris-prener.github.io/biscale/
cowplot R package https://wilkelab.org/cowplot/articles/drawing_with_on_plots.html#absolute-positioning

Library

To begin, we will need to install a few new packages and load some packages that we’ve previously installed:

Code

utils::install.packages("cluster")
utils::install.packages("factoextra")
utils::install.packages("gridExtra")
utils::install.packages("biscale")
utils::install.packages("cowplot")

Code

# Turn off scientific notation
options(scipen=999)

# Load packages
library(here)        # relative file paths for reproducibility
library(tidyverse)   # data wrangling
library(stringi)     # string data wrangling
library(tigris)      # US census TIGER/Line shapefiles
library(ggplot2)     # data visualization
library(cowplot)     # data visualization plotting
library(gridExtra)   # grid for data visualizations
library(biscale)     # bivariate mapping
library(kableExtra)  # table formatting
library(scales)      # palette and number formatting
library(cluster)     # clustering algorithms
library(factoextra)  # clustering algorithms & visualization

Functions and Constant Variables

Next we need to import our functions and constants from our project_data_steps.R file. Remember, your file should have your initials at the end to avoid confusion with your teammates. For example, in a shared repo my file name would be project_data_steps_CS.R

Recall that we should use the here::here() function for relative file paths. We also can use double colons :: to indicate both the specific library and function name we want to use to avoid any overriding.

Import Functions

Code

import::here( "fips_census_regions",
              "load_svi_data",
              "merge_svi_data",
              "census_division",
              "flag_summarize",
             # notice the use of here::here() that points to the .R file
             # where all these R objects are created
             .from = here::here("analysis/project_data_steps.R"),
             .character_only = TRUE)

census_division

Data

Next, recall that we can load up our data sets and process them with our functions to create data sets on a national and divisional level for 2010 and 2020.

Note

Note that we will want to flag our SVI indicators at or above the 75th percentile. For the divisional data we will also want to utilize the rank_by and location parameters to limit to our division of interest.

Code

# Load SVI data sets
svi_2010 <- readRDS(here::here("data/raw/Census_Data_SVI/svi_2010_trt10.rds"))
svi_2020 <- readRDS(here::here("data/raw/Census_Data_SVI/svi_2020_trt10.rds"))

# Load mapping data sets
svi_county_map2010 <- readRDS(here::here(paste0("data/wrangling/", str_replace_all(census_division, " ", "_"), "_county_svi_flags10.rds")))

svi_county_map2020 <- readRDS(here::here(paste0("data/wrangling/", str_replace_all(census_division, " ", "_"), "_county_svi_flags20.rds")))

divisional_st_sf <- readRDS(here::here(paste0("data/wrangling/", str_replace_all(census_division, " ", "_"), "_st_sf.rds")))

Code

# Load NMTC & LIHTC Tract Eligibility Data

orig_nmtc <- readxl::read_excel(here::here("data/raw/NMTC_LIHTC_tracts/nmtc_2011-2015_lic_110217.xlsx"), sheet="NMTC LICs 2011-2015 ACS")

high_migration_nmtc <- readxl::read_excel(here::here("data/raw/NMTC_LIHTC_tracts/nmtc_2011-2015_lic_110217.xlsx"), sheet="High migration tracts", skip=1)

nmtc_awards_data <- readxl::read_excel(here::here("data/raw/NMTC_LIHTC_tracts/NMTC_Public_Data_Release_includes_FY_2021_Data_final.xlsx"), sheet = "Projects 2 - Data Set PUBLISH.P")

lihtc_eligible <- readxl::read_excel(here::here("data/raw/NMTC_LIHTC_tracts/qct_data_2010_2011_2012.xlsx"))

lihtc_projects <- read.csv(here::here("data/raw/NMTC_LIHTC_tracts/lihtcpub/LIHTCPUB.csv"))

Load 2010 SVI Data

Code

# National 2010 Data
svi_2010_national <- load_svi_data(svi_2010, percentile=.75)
svi_2010_national %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID_2010_trt	FIPS_st	FIPS_county	FIPS_tract	state	state_name	county	region_number	region	division_number	division	E_TOTPOP_10	E_HU_10	E_HH_10	E_POV150_10	ET_POVSTATUS_10	EP_POV150_10	EPL_POV150_10	E_UNEMP_10	ET_EMPSTATUS_10	EP_UNEMP_10	EPL_UNEMP_10	E_HBURD_OWN_10	ET_HOUSINGCOST_OWN_10	EP_HBURD_OWN_10	EPL_HBURD_OWN_10	E_HBURD_RENT_10	ET_HOUSINGCOST_RENT_10	EP_HBURD_RENT_10	EPL_HBURD_RENT_10	E_HBURD_10	ET_HOUSINGCOST_10	EP_HBURD_10	EPL_HBURD_10	E_NOHSDP_10	ET_EDSTATUS_10	EP_NOHSDP_10	EPL_NOHSDP_10	F_NOHSDP_10	E_UNINSUR_12	ET_INSURSTATUS_12	EP_UNINSUR_12	EPL_UNINSUR_12	E_AGE65_10	EP_AGE65_10	EPL_AGE65_10	F_AGE65_10	E_AGE17_10	EP_AGE17_10	EPL_AGE17_10	F_AGE17_10	E_DISABL_12	ET_DISABLSTATUS_12	EP_DISABL_12	EPL_DISABL_12	F_DISABL_12	E_SNGPNT_10	ET_FAMILIES_10	EP_SNGPNT_10	EPL_SNGPNT_10	F_SNGPNT_10	E_LIMENG_10	ET_POPAGE5UP_10	EP_LIMENG_10	EPL_LIMENG_10	E_MINRTY_10	ET_POPETHRACE_10	EP_MINRTY_10	EPL_MINRTY_10	F_MINRTY_10	E_STRHU_10	E_MUNIT_10	EP_MUNIT_10	EPL_MUNIT_10	E_MOBILE_10	EP_MOBILE_10	EPL_MOBILE_10	F_MOBILE_10	E_CROWD_10	ET_OCCUPANTS_10	EP_CROWD_10	EPL_CROWD_10	E_NOVEH_10	ET_KNOWNVEH_10	EP_NOVEH_10	EPL_NOVEH_10	F_NOVEH_10	ET_HHTYPE_10	EPL_GROUPQ_10	SPL_THEME1	RPL_THEME1	F_THEME1	SPL_THEME2	RPL_THEME2	F_THEME2	SPL_THEME3	RPL_THEME3	F_THEME3	SPL_THEME4	RPL_THEME4	F_THEME4	SPL_THEMES	RPL_THEMES	F_TOTAL
01001020100	01	001	020100	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	1809	771	696	297	1809	16.41791	0.3871	36	889	4.049494	0.1790	127	598	21.23746	0.20770	47	98	47.95918	0.5767	174	696	25.00000	0.18790	196	1242	15.780998	0.6093	0	186	1759	10.574190	0.3790	222	12.271973	0.4876	0	445	24.59923	0.5473	0	298	1335	22.32210	0.8454	1	27	545	4.954128	0.09275	0	36	1705	2.1114370	0.59040	385	1809	21.282477	0.4524	0	771	0	0.0000000	0.1224	92	11.9325551	0.8005	1	0	696	0.0000000	0.1238	50	696	7.183908	0.6134	0	1809	0.364	1.74230	0.28200	0	2.56345	0.5296	1	0.4524	0.4482	0	2.0241	0.2519	1	6.78225	0.3278	2
01001020200	01	001	020200	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	2020	816	730	495	1992	24.84940	0.5954	68	834	8.153477	0.5754	49	439	11.16173	0.02067	105	291	36.08247	0.3019	154	730	21.09589	0.09312	339	1265	26.798419	0.8392	1	313	2012	15.556660	0.6000	204	10.099010	0.3419	0	597	29.55446	0.8192	1	359	1515	23.69637	0.8791	1	132	456	28.947368	0.83510	1	15	1890	0.7936508	0.40130	1243	2020	61.534653	0.7781	1	816	0	0.0000000	0.1224	34	4.1666667	0.6664	0	13	730	1.7808219	0.5406	115	730	15.753425	0.8382	1	2020	0.364	2.70312	0.56650	1	3.27660	0.8614	3	0.7781	0.7709	1	2.5316	0.5047	1	9.28942	0.6832	6
01001020300	01	001	020300	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	3543	1403	1287	656	3533	18.56779	0.4443	93	1552	5.992268	0.3724	273	957	28.52665	0.45780	178	330	53.93939	0.7152	451	1287	35.04274	0.49930	346	2260	15.309734	0.5950	0	252	3102	8.123791	0.2596	487	13.745413	0.5868	0	998	28.16822	0.7606	1	371	2224	16.68165	0.6266	0	126	913	13.800657	0.46350	0	0	3365	0.0000000	0.09298	637	3543	17.979114	0.4049	0	1403	10	0.7127584	0.3015	2	0.1425517	0.4407	0	0	1287	0.0000000	0.1238	101	1287	7.847708	0.6443	0	3543	0.364	2.17060	0.41010	0	2.53048	0.5116	1	0.4049	0.4011	0	1.8743	0.1942	0	6.98028	0.3576	1
01001020400	01	001	020400	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	4840	1957	1839	501	4840	10.35124	0.2177	101	2129	4.744011	0.2447	310	1549	20.01291	0.17080	89	290	30.68966	0.2044	399	1839	21.69657	0.10540	274	3280	8.353658	0.3205	0	399	4293	9.294200	0.3171	955	19.731405	0.8643	1	1195	24.69008	0.5530	0	625	3328	18.78005	0.7233	0	152	1374	11.062591	0.34710	0	10	4537	0.2204100	0.22560	297	4840	6.136364	0.1647	0	1957	33	1.6862545	0.3843	25	1.2774655	0.5516	0	14	1839	0.7612833	0.3564	19	1839	1.033170	0.1127	0	4840	0.364	1.20540	0.13470	0	2.71330	0.6129	1	0.1647	0.1632	0	1.7690	0.1591	0	5.85240	0.1954	1
01001020500	01	001	020500	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	9938	3969	3741	1096	9938	11.02838	0.2364	188	4937	3.807981	0.1577	426	2406	17.70574	0.11050	528	1335	39.55056	0.3753	954	3741	25.50120	0.20140	293	5983	4.897209	0.1655	0	740	10110	7.319486	0.2211	837	8.422218	0.2408	0	3012	30.30791	0.8455	1	759	7155	10.60797	0.2668	0	476	2529	18.821669	0.63540	0	78	9297	0.8389803	0.41110	1970	9938	19.822902	0.4330	0	3969	306	7.7097506	0.6153	0	0.0000000	0.2198	0	7	3741	0.1871157	0.2535	223	3741	5.960973	0.5483	0	9938	0.364	0.98210	0.08468	0	2.39960	0.4381	1	0.4330	0.4290	0	2.0009	0.2430	0	5.81560	0.1905	1
01001020600	01	001	020600	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	3402	1456	1308	735	3402	21.60494	0.5199	134	1720	7.790698	0.5436	242	1032	23.44961	0.28010	62	276	22.46377	0.1035	304	1308	23.24159	0.14070	301	2151	13.993491	0.5510	0	355	3445	10.304790	0.3656	386	11.346267	0.4232	0	931	27.36626	0.7200	0	440	2439	18.04018	0.6912	0	143	924	15.476190	0.52900	0	4	3254	0.1229256	0.19840	723	3402	21.252205	0.4519	0	1456	18	1.2362637	0.3507	433	29.7390110	0.9468	1	16	1308	1.2232416	0.4493	28	1308	2.140673	0.2298	0	3402	0.364	2.12080	0.39510	0	2.56180	0.5288	0	0.4519	0.4477	0	2.3406	0.4048	1	7.47510	0.4314	1

Code

# Divisional 2010 Data
svi_2010_divisional <- load_svi_data(svi_2010, rank_by = "divisional", location = census_division, percentile=.75)
svi_2010_divisional %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID_2010_trt	FIPS_st	FIPS_county	FIPS_tract	state	state_name	county	region_number	region	division_number	division	E_TOTPOP_10	E_HU_10	E_HH_10	E_POV150_10	ET_POVSTATUS_10	EP_POV150_10	EPL_POV150_10	F_POV150_10	E_UNEMP_10	ET_EMPSTATUS_10	EP_UNEMP_10	EPL_UNEMP_10	F_UNEMP_10	E_HBURD_OWN_10	ET_HOUSINGCOST_OWN_10	EP_HBURD_OWN_10	EPL_HBURD_OWN_10	F_HBURD_OWN_10	E_HBURD_RENT_10	ET_HOUSINGCOST_RENT_10	EP_HBURD_RENT_10	EPL_HBURD_RENT_10	F_HBURD_RENT_10	E_HBURD_10	ET_HOUSINGCOST_10	EP_HBURD_10	EPL_HBURD_10	F_HBURD_10	E_NOHSDP_10	ET_EDSTATUS_10	EP_NOHSDP_10	EPL_NOHSDP_10	F_NOHSDP_10	E_UNINSUR_12	ET_INSURSTATUS_12	EP_UNINSUR_12	EPL_UNINSUR_12	F_UNINSUR_12	E_AGE65_10	EP_AGE65_10	EPL_AGE65_10	F_AGE65_10	E_AGE17_10	EP_AGE17_10	EPL_AGE17_10	F_AGE17_10	E_DISABL_12	ET_DISABLSTATUS_12	EP_DISABL_12	EPL_DISABL_12	F_DISABL_12	E_SNGPNT_10	ET_FAMILIES_10	EP_SNGPNT_10	EPL_SNGPNT_10	F_SNGPNT_10	E_LIMENG_10	ET_POPAGE5UP_10	EP_LIMENG_10	EPL_LIMENG_10	F_LIMENG_10	E_MINRTY_10	ET_POPETHRACE_10	EP_MINRTY_10	EPL_MINRTY_10	F_MINRTY_10	E_STRHU_10	E_MUNIT_10	EP_MUNIT_10	EPL_MUNIT_10	F_MUNIT_10	E_MOBILE_10	EP_MOBILE_10	EPL_MOBILE_10	E_CROWD_10	ET_OCCUPANTS_10	EP_CROWD_10	EPL_CROWD_10	F_CROWD_10	E_NOVEH_10	ET_KNOWNVEH_10	EP_NOVEH_10	EPL_NOVEH_10	F_NOVEH_10	E_GROUPQ_10	ET_HHTYPE_10	EP_GROUPQ_10	EPL_GROUPQ_10	F_GROUPQ_10	SPL_THEME1	RPL_THEME1	F_THEME1	SPL_THEME2	RPL_THEME2	F_THEME2	SPL_THEME3	RPL_THEME3	F_THEME3	SPL_THEME4	RPL_THEME4	F_THEME4	SPL_THEMES	RPL_THEMES	F_TOTAL
34001000100	34	001	000100	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2907	1088	983	1127	2907	38.76849	0.8482	1	144	1433	10.048849	0.7544	1	280	435	64.36782	0.9529	1	204	548	37.22628	0.2998	0	484	983	49.23703	0.7813	1	468	1759	26.60603	0.8634	1	532	2543	20.92017	0.8978	1	250	8.599931	0.1777	0	944	32.47334	0.94170	1	186	1851	10.04862	0.2706	0	266	678	39.233038	0.8981	1	177	2611	6.779012	0.7778	1	1928	2907	66.32267	0.7743	1	1088	113	10.386029	0.6229	0	9	0.8272059	0.7223	80	983	8.138352	0.8657	1	265	983	26.95829	0.7354	0	0	2907	0.000000	0.3512	0	4.1451	0.8935	5	3.06590	0.7944	3	0.7743	0.7667	1	3.2975	0.8414	1	11.28280	0.8862	10
34001000200	34	001	000200	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3189	2217	1473	519	3189	16.27469	0.4806	0	109	1558	6.996149	0.5179	0	573	955	60.00000	0.9323	1	199	518	38.41699	0.3261	0	772	1473	52.41005	0.8418	1	405	2579	15.70376	0.6491	0	484	3547	13.64533	0.7154	0	847	26.560050	0.9629	1	436	13.67200	0.08181	0	608	3005	20.23295	0.8466	1	42	857	4.900817	0.1204	0	422	3072	13.736979	0.8799	1	1792	3189	56.19316	0.7390	0	2217	901	40.640505	0.8693	1	0	0.0000000	0.3251	48	1473	3.258656	0.7064	0	250	1473	16.97217	0.6444	0	0	3189	0.000000	0.3512	0	3.2048	0.6963	1	2.89161	0.7231	3	0.7390	0.7317	0	2.8964	0.6887	1	9.73181	0.7340	5
34001000300	34	001	000300	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3997	1823	1357	1401	3968	35.30746	0.8164	1	382	2238	17.068811	0.9376	1	176	329	53.49544	0.8855	1	604	1028	58.75486	0.7947	1	780	1357	57.47973	0.9165	1	920	2677	34.36683	0.9346	1	1351	4149	32.56206	0.9811	1	314	7.855892	0.1437	0	937	23.44258	0.55900	0	319	3054	10.44532	0.3000	0	187	782	23.913044	0.7498	0	1080	3671	29.419777	0.9742	1	3357	3997	83.98799	0.8419	1	1823	363	19.912233	0.7535	1	0	0.0000000	0.3251	150	1357	11.053795	0.9136	1	651	1357	47.97347	0.8585	1	0	3997	0.000000	0.3512	0	4.5862	0.9691	5	2.72670	0.6360	1	0.8419	0.8336	1	3.2019	0.8054	3	11.35670	0.8920	10
34001000400	34	001	000400	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2902	2683	1401	1172	2902	40.38594	0.8615	1	190	1389	13.678906	0.8811	1	364	707	51.48515	0.8627	1	507	694	73.05476	0.9503	1	871	1401	62.16988	0.9572	1	481	1981	24.28067	0.8339	1	674	3204	21.03620	0.8998	1	434	14.955203	0.6083	0	596	20.53756	0.33980	0	426	2607	16.34062	0.6886	0	111	652	17.024540	0.6204	0	215	2736	7.858187	0.8008	1	1792	2902	61.75052	0.7584	1	2683	2049	76.369735	0.9401	1	0	0.0000000	0.3251	69	1401	4.925053	0.7847	1	511	1401	36.47395	0.7992	1	72	2902	2.481048	0.8114	1	4.4335	0.9468	5	3.05790	0.7908	1	0.7584	0.7510	1	3.6605	0.9391	4	11.91030	0.9339	11
34001000500	34	001	000500	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3483	1241	1027	1938	3483	55.64169	0.9533	1	124	1630	7.607362	0.5830	0	227	446	50.89686	0.8549	1	478	581	82.27194	0.9799	1	705	1027	68.64654	0.9863	1	733	2077	35.29129	0.9396	1	727	3258	22.31430	0.9149	1	377	10.824002	0.3081	0	1055	30.28998	0.90140	1	268	2401	11.16202	0.3549	0	209	763	27.391874	0.7940	1	911	3077	29.606760	0.9746	1	3036	3483	87.16624	0.8550	1	1241	52	4.190169	0.4505	0	4	0.3223207	0.6567	113	1027	11.002921	0.9128	1	422	1027	41.09056	0.8250	1	0	3483	0.000000	0.3512	0	4.3771	0.9379	4	3.33300	0.8766	3	0.8550	0.8467	1	3.1962	0.8026	2	11.76130	0.9229	10
34001001100	34	001	001100	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2204	1204	1204	1185	2204	53.76588	0.9457	1	219	927	23.624596	0.9830	1	97	172	56.39535	0.9094	1	462	1032	44.76744	0.4746	0	559	1204	46.42857	0.7197	0	346	1440	24.02778	0.8306	1	469	1942	24.15036	0.9360	1	363	16.470054	0.7020	0	578	26.22505	0.74410	0	442	1558	28.36970	0.9675	1	247	396	62.373737	0.9898	1	104	2051	5.070697	0.7260	0	2118	2204	96.09800	0.9204	1	1204	570	47.342193	0.8858	1	0	0.0000000	0.3251	14	1204	1.162791	0.4877	0	817	1204	67.85714	0.9413	1	0	2204	0.000000	0.3512	0	4.4150	0.9451	4	4.12940	0.9805	2	0.9204	0.9114	1	2.9911	0.7243	2	12.45590	0.9597	9

Load 2020 SVI Data

Code

# National 2020 Data
svi_2020_national <- load_svi_data(svi_2020, percentile=.75)
svi_2020_national %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID_2010_trt	FIPS_st	FIPS_county	FIPS_tract	state	state_name	county	region_number	region	division_number	division	E_TOTPOP_20	E_HU_20	E_HH_20	E_POV150_20	ET_POVSTATUS_20	EP_POV150_20	EPL_POV150_20	F_POV150_20	E_UNEMP_20	ET_EMPSTATUS_20	EP_UNEMP_20	EPL_UNEMP_20	E_HBURD_OWN_20	ET_HOUSINGCOST_OWN_20	EP_HBURD_OWN_20	EPL_HBURD_OWN_20	F_HBURD_OWN_20	E_HBURD_RENT_20	ET_HOUSINGCOST_RENT_20	EP_HBURD_RENT_20	EPL_HBURD_RENT_20	F_HBURD_RENT_20	E_HBURD_20	ET_HOUSINGCOST_20	EP_HBURD_20	EPL_HBURD_20	E_NOHSDP_20	ET_EDSTATUS_20	EP_NOHSDP_20	EPL_NOHSDP_20	E_UNINSUR_20	ET_INSURSTATUS_20	EP_UNINSUR_20	EPL_UNINSUR_20	F_UNINSUR_20	E_AGE65_20	EP_AGE65_20	EPL_AGE65_20	F_AGE65_20	E_AGE17_20	EP_AGE17_20	EPL_AGE17_20	F_AGE17_20	E_DISABL_20	ET_DISABLSTATUS_20	EP_DISABL_20	EPL_DISABL_20	F_DISABL_20	E_SNGPNT_20	ET_FAMILIES_20	EP_SNGPNT_20	EPL_SNGPNT_20	F_SNGPNT_20	E_LIMENG_20	ET_POPAGE5UP_20	EP_LIMENG_20	EPL_LIMENG_20	E_MINRTY_20	ET_POPETHRACE_20	EP_MINRTY_20	EPL_MINRTY_20	F_MINRTY_20	E_STRHU_20	E_MUNIT_20	EP_MUNIT_20	EPL_MUNIT_20	E_MOBILE_20	EP_MOBILE_20	EPL_MOBILE_20	F_MOBILE_20	E_CROWD_20	ET_OCCUPANTS_20	EP_CROWD_20	EPL_CROWD_20	E_NOVEH_20	ET_KNOWNVEH_20	EP_NOVEH_20	EPL_NOVEH_20	E_GROUPQ_20	ET_HHTYPE_20	EP_GROUPQ_20	EPL_GROUPQ_20	F_GROUPQ_20	SPL_THEME1	RPL_THEME1	F_THEME1	SPL_THEME2	RPL_THEME2	F_THEME2	SPL_THEME3	RPL_THEME3	F_THEME3	SPL_THEME4	RPL_THEME4	F_THEME4	SPL_THEMES	RPL_THEMES	F_TOTAL
01001020100	01	001	020100	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	1941	710	693	352	1941	18.13498	0.4630	0	18	852	2.112676	0.15070	81	507	15.976331	0.26320	0	63	186	33.87097	0.2913	0	144	693	20.77922	0.2230	187	1309	14.285714	0.6928	187	1941	9.634209	0.6617	0	295	15.19835	0.4601	0	415	21.38073	0.4681	0	391	1526	25.62254	0.9011	1	58	555	10.45045	0.3451	0	0	1843	0.0000000	0.09479	437	1941	22.51417	0.3902	0	710	0	0.0000000	0.1079	88	12.3943662	0.8263	1	0	693	0.0000000	0.09796	10	693	1.443001	0.1643	0	1941	0.000000	0.1831	0	2.19120	0.4084	0	2.26919	0.3503	1	0.3902	0.3869	0	1.37956	0.07216	1	6.23015	0.2314	2
01001020200	01	001	020200	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	1757	720	573	384	1511	25.41363	0.6427	0	29	717	4.044630	0.41320	33	392	8.418367	0.03542	0	116	181	64.08840	0.9086	1	149	573	26.00349	0.4041	139	1313	10.586443	0.5601	91	1533	5.936073	0.4343	0	284	16.16392	0.5169	0	325	18.49744	0.2851	0	164	1208	13.57616	0.4127	0	42	359	11.69916	0.3998	0	0	1651	0.0000000	0.09479	1116	1757	63.51736	0.7591	1	720	3	0.4166667	0.2470	5	0.6944444	0.5106	0	9	573	1.5706806	0.46880	57	573	9.947644	0.7317	212	1757	12.066022	0.9549	1	2.45440	0.4888	0	1.70929	0.1025	0	0.7591	0.7527	1	2.91300	0.68620	1	7.83579	0.4802	2
01001020300	01	001	020300	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	3694	1464	1351	842	3694	22.79372	0.5833	0	53	1994	2.657974	0.22050	117	967	12.099276	0.11370	0	147	384	38.28125	0.3856	0	264	1351	19.54108	0.1827	317	2477	12.797739	0.6460	127	3673	3.457664	0.2308	0	464	12.56091	0.3088	0	929	25.14889	0.7080	0	473	2744	17.23761	0.6211	0	263	975	26.97436	0.8234	1	128	3586	3.5694367	0.70770	1331	3694	36.03140	0.5515	0	1464	26	1.7759563	0.3675	14	0.9562842	0.5389	0	35	1351	2.5906736	0.60550	42	1351	3.108808	0.3415	0	3694	0.000000	0.1831	0	1.86330	0.3063	0	3.16900	0.8380	1	0.5515	0.5468	0	2.03650	0.26830	0	7.62030	0.4460	1
01001020400	01	001	020400	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	3539	1741	1636	503	3539	14.21305	0.3472	0	39	1658	2.352232	0.17990	219	1290	16.976744	0.30880	0	74	346	21.38728	0.1037	0	293	1636	17.90954	0.1333	173	2775	6.234234	0.3351	169	3529	4.788892	0.3448	0	969	27.38062	0.9225	1	510	14.41085	0.1208	0	670	3019	22.19278	0.8194	1	148	1137	13.01671	0.4541	0	89	3409	2.6107363	0.64690	454	3539	12.82848	0.2364	0	1741	143	8.2136703	0.6028	0	0.0000000	0.2186	0	10	1636	0.6112469	0.28340	72	1636	4.400978	0.4538	0	3539	0.000000	0.1831	0	1.34030	0.1575	0	2.96370	0.7496	2	0.2364	0.2344	0	1.74170	0.16270	0	6.28210	0.2389	2
01001020500	01	001	020500	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	10674	4504	4424	1626	10509	15.47245	0.3851	0	81	5048	1.604596	0.09431	321	2299	13.962592	0.17970	0	711	2125	33.45882	0.2836	0	1032	4424	23.32731	0.3109	531	6816	7.790493	0.4251	301	10046	2.996217	0.1894	0	1613	15.11149	0.4553	0	2765	25.90407	0.7494	0	1124	7281	15.43744	0.5253	0	342	2912	11.74451	0.4019	0	52	9920	0.5241935	0.35230	2603	10674	24.38636	0.4160	0	4504	703	15.6083481	0.7378	29	0.6438721	0.5037	0	37	4424	0.8363472	0.33420	207	4424	4.679023	0.4754	176	10674	1.648866	0.7598	1	1.40481	0.1743	0	2.48420	0.4802	0	0.4160	0.4125	0	2.81090	0.63730	1	7.11591	0.3654	1
01001020600	01	001	020600	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	3536	1464	1330	1279	3523	36.30429	0.8215	1	34	1223	2.780049	0.23780	321	1111	28.892889	0.75870	1	67	219	30.59361	0.2305	0	388	1330	29.17293	0.5075	306	2380	12.857143	0.6480	415	3496	11.870709	0.7535	1	547	15.46946	0.4760	0	982	27.77149	0.8327	1	729	2514	28.99761	0.9488	1	95	880	10.79545	0.3601	0	0	3394	0.0000000	0.09479	985	3536	27.85633	0.4608	0	1464	0	0.0000000	0.1079	364	24.8633880	0.9300	1	0	1330	0.0000000	0.09796	17	1330	1.278196	0.1463	0	3536	0.000000	0.1831	0	2.96830	0.6434	2	2.71239	0.6156	2	0.4608	0.4569	0	1.46526	0.08976	1	7.60675	0.4440	5

Code

# Divisional 2020 Data
svi_2020_divisional <- load_svi_data(svi_2020, rank_by = "divisional", location =  census_division, percentile=.75)
svi_2020_divisional %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID_2010_trt	FIPS_st	FIPS_county	FIPS_tract	state	state_name	county	region_number	region	division_number	division	E_TOTPOP_20	E_HU_20	E_HH_20	E_POV150_20	ET_POVSTATUS_20	EP_POV150_20	EPL_POV150_20	F_POV150_20	E_UNEMP_20	ET_EMPSTATUS_20	EP_UNEMP_20	EPL_UNEMP_20	F_UNEMP_20	E_HBURD_OWN_20	ET_HOUSINGCOST_OWN_20	EP_HBURD_OWN_20	EPL_HBURD_OWN_20	F_HBURD_OWN_20	E_HBURD_RENT_20	ET_HOUSINGCOST_RENT_20	EP_HBURD_RENT_20	EPL_HBURD_RENT_20	F_HBURD_RENT_20	E_HBURD_20	ET_HOUSINGCOST_20	EP_HBURD_20	EPL_HBURD_20	F_HBURD_20	E_NOHSDP_20	ET_EDSTATUS_20	EP_NOHSDP_20	EPL_NOHSDP_20	F_NOHSDP_20	E_UNINSUR_20	ET_INSURSTATUS_20	EP_UNINSUR_20	EPL_UNINSUR_20	F_UNINSUR_20	E_AGE65_20	EP_AGE65_20	EPL_AGE65_20	E_AGE17_20	EP_AGE17_20	EPL_AGE17_20	F_AGE17_20	E_DISABL_20	ET_DISABLSTATUS_20	EP_DISABL_20	EPL_DISABL_20	F_DISABL_20	E_SNGPNT_20	ET_FAMILIES_20	EP_SNGPNT_20	EPL_SNGPNT_20	F_SNGPNT_20	E_LIMENG_20	ET_POPAGE5UP_20	EP_LIMENG_20	EPL_LIMENG_20	F_LIMENG_20	E_MINRTY_20	ET_POPETHRACE_20	EP_MINRTY_20	EPL_MINRTY_20	F_MINRTY_20	E_STRHU_20	E_MUNIT_20	EP_MUNIT_20	EPL_MUNIT_20	F_MUNIT_20	E_MOBILE_20	EP_MOBILE_20	EPL_MOBILE_20	E_CROWD_20	ET_OCCUPANTS_20	EP_CROWD_20	EPL_CROWD_20	F_CROWD_20	E_NOVEH_20	ET_KNOWNVEH_20	EP_NOVEH_20	EPL_NOVEH_20	F_NOVEH_20	E_GROUPQ_20	ET_HHTYPE_20	EP_GROUPQ_20	EPL_GROUPQ_20	SPL_THEME1	RPL_THEME1	F_THEME1	SPL_THEME2	RPL_THEME2	F_THEME2	SPL_THEME3	RPL_THEME3	F_THEME3	SPL_THEME4	RPL_THEME4	F_THEME4	SPL_THEMES	RPL_THEMES	F_TOTAL
34001000100	34	001	000100	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2157	941	784	1182	2157	54.79833	0.9571	1	242	1058	22.873346	0.9922	1	215	342	62.86550	0.9780	1	316	442	71.49321	0.9481	1	531	784	67.72959	0.9893	1	396	1274	31.08320	0.9497	1	266	2157	12.331943	0.9041	1	185	8.576727	0.09430	552	25.59110	0.8128	1	297	1605	18.504673	0.74880	0	83	510	16.27451	0.6090	0	251	2020	12.425743	0.8710	1	1852	2157	85.85999	0.8476	1	941	118	12.5398512	0.6385	0	0	0.0000000	0.3216	67	784	8.545918	0.8657	1	212	784	27.04082	0.7502	1	0	2157	0.0000000	0.1517	4.7924	0.9850	5	3.13590	0.8217	2	0.8476	0.8400	1	2.7277	0.6085	2	11.50360	0.9104	10
34001000200	34	001	000200	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3510	2046	1353	1021	3510	29.08832	0.7682	1	121	1852	6.533477	0.6717	0	343	696	49.28161	0.9273	1	416	657	63.31811	0.8696	1	759	1353	56.09756	0.9321	1	553	2338	23.65269	0.8871	1	354	3510	10.085470	0.8530	1	643	18.319088	0.60310	1002	28.54701	0.9055	1	450	2508	17.942584	0.72330	0	237	786	30.15267	0.8539	1	534	3375	15.822222	0.9062	1	2534	3510	72.19373	0.7818	1	2046	906	44.2815249	0.8690	1	0	0.0000000	0.3216	119	1353	8.795270	0.8711	1	324	1353	23.94678	0.7255	0	0	3510	0.0000000	0.1517	4.1121	0.9003	4	3.99200	0.9781	3	0.7818	0.7747	1	2.9389	0.7011	2	11.82480	0.9310	10
34001000300	34	001	000300	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3801	1640	1226	1857	3801	48.85556	0.9333	1	226	1800	12.555556	0.9267	1	111	280	39.64286	0.8339	1	608	946	64.27061	0.8842	1	719	1226	58.64600	0.9528	1	650	2275	28.57143	0.9337	1	1027	3801	27.019206	0.9914	1	380	9.997369	0.14040	1223	32.17574	0.9607	1	219	2578	8.494957	0.15680	0	268	909	29.48295	0.8456	1	940	3400	27.647059	0.9728	1	3318	3801	87.29282	0.8579	1	1640	262	15.9756098	0.6917	0	0	0.0000000	0.3216	124	1226	10.114192	0.8955	1	477	1226	38.90701	0.8258	1	0	3801	0.0000000	0.1517	4.7379	0.9829	5	3.07630	0.8013	3	0.8579	0.8501	1	2.8863	0.6781	2	11.55840	0.9150	11
34001000400	34	001	000400	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3178	2264	1390	1508	3176	47.48111	0.9246	1	172	1804	9.534368	0.8460	1	205	468	43.80342	0.8858	1	622	922	67.46204	0.9192	1	827	1390	59.49640	0.9587	1	364	2076	17.53372	0.8013	1	476	3178	14.977974	0.9390	1	483	15.198238	0.41220	539	16.96035	0.2484	0	319	2639	12.087912	0.38790	0	101	565	17.87611	0.6539	0	583	3022	19.291860	0.9349	1	2186	3178	68.78540	0.7658	1	2264	1609	71.0689046	0.9266	1	15	0.6625442	0.7078	226	1390	16.258993	0.9567	1	599	1390	43.09353	0.8474	1	20	3178	0.6293266	0.6292	4.4696	0.9558	5	2.63730	0.5864	1	0.7658	0.7588	1	4.0677	0.9762	3	11.94040	0.9387	10
34001000500	34	001	000500	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3385	1185	945	1682	3364	50.00000	0.9391	1	72	1577	4.565631	0.4586	0	185	468	39.52991	0.8332	1	362	477	75.89099	0.9703	1	547	945	57.88360	0.9477	1	592	1983	29.85376	0.9422	1	738	3385	21.802068	0.9817	1	240	7.090103	0.05988	1129	33.35303	0.9689	1	135	2256	5.984043	0.04817	0	110	717	15.34170	0.5822	0	721	3076	23.439532	0.9569	1	3029	3385	89.48301	0.8727	1	1185	9	0.7594937	0.2382	0	0	0.0000000	0.3216	103	945	10.899471	0.9072	1	263	945	27.83069	0.7560	1	0	3385	0.0000000	0.1517	4.2693	0.9283	4	2.61605	0.5709	2	0.8727	0.8648	1	2.3747	0.4357	2	10.13275	0.7921	9
34001001100	34	001	001100	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	1950	1267	1096	1131	1950	58.00000	0.9678	1	66	706	9.348442	0.8395	1	42	101	41.58416	0.8612	1	309	995	31.05528	0.1959	0	351	1096	32.02555	0.4782	0	510	1379	36.98332	0.9763	1	155	1950	7.948718	0.7660	1	392	20.102564	0.69880	447	22.92308	0.6712	0	570	1503	37.924152	0.99200	1	143	374	38.23529	0.9167	1	109	1841	5.920695	0.7464	0	1909	1950	97.89744	0.9529	1	1267	479	37.8058406	0.8464	1	0	0.0000000	0.3216	33	1096	3.010949	0.6446	0	743	1096	67.79197	0.9414	1	0	1950	0.0000000	0.1517	4.0278	0.8848	4	4.02510	0.9798	2	0.9529	0.9442	1	2.9057	0.6869	2	11.91150	0.9365	9

Check Data

Next, we want to check that our functions are behaving as expected and have filtered our data sets to include all divisions and states on the national level and only our division/states of interest on the divisional level:

2010

Code

svi_2010_national$division %>% unique()

[1] "East South Central Division" "Pacific Division"           
[3] "Mountain Division"           "West South Central Division"
[5] "New England Division"        "South Atlantic Division"    
[7] "East North Central Division" "West North Central Division"
[9] "Middle Atlantic Division"

Code

svi_2010_national$state %>% unique()

 [1] "AL" "AK" "AZ" "AR" "CA" "CO" "CT" "DE" "DC" "FL" "GA" "HI" "ID" "IL" "IN"
[16] "IA" "KS" "KY" "LA" "ME" "MD" "MA" "MI" "MN" "MS" "MO" "MT" "NE" "NV" "NH"
[31] "NJ" "NM" "NY" "NC" "ND" "OH" "OK" "OR" "PA" "RI" "SC" "SD" "TN" "TX" "UT"
[46] "VT" "VA" "WA" "WV" "WI" "WY"

Code

svi_2010_divisional$division %>% unique()

[1] "Middle Atlantic Division"

Code

svi_2010_divisional$state %>% unique()

[1] "NJ" "NY" "PA"

2020

Code

svi_2020_national$division %>% unique()

[1] "East South Central Division" "Pacific Division"           
[3] "Mountain Division"           "West South Central Division"
[5] "New England Division"        "South Atlantic Division"    
[7] "East North Central Division" "West North Central Division"
[9] "Middle Atlantic Division"

Code

svi_2020_national$state %>% unique()

 [1] "AL" "AK" "AZ" "AR" "CA" "CO" "CT" "DE" "DC" "FL" "GA" "HI" "ID" "IL" "IN"
[16] "IA" "KS" "KY" "LA" "ME" "MD" "MA" "MI" "MN" "MS" "MO" "MT" "NE" "NV" "NH"
[31] "NJ" "NM" "NY" "NC" "ND" "OH" "OK" "OR" "PA" "RI" "SC" "SD" "TN" "TX" "UT"
[46] "VT" "VA" "WA" "WV" "WI" "WY"

Code

svi_2020_divisional$division %>% unique()

[1] "Middle Atlantic Division"

Code

svi_2020_divisional$state %>% unique()

[1] "NJ" "NY" "PA"

Merge 2010 and 2020 data

Code

# Find tracts with divisional data in both 2010 and 2020
svi_divisional <- merge_svi_data(svi_2010_divisional, svi_2020_divisional)
svi_divisional %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID_2010_trt	FIPS_st	FIPS_county	FIPS_tract	state	state_name	county	region_number	region	division_number	division	E_TOTPOP_10	E_HU_10	E_HH_10	E_POV150_10	ET_POVSTATUS_10	EP_POV150_10	EPL_POV150_10	F_POV150_10	E_UNEMP_10	ET_EMPSTATUS_10	EP_UNEMP_10	EPL_UNEMP_10	F_UNEMP_10	E_HBURD_OWN_10	ET_HOUSINGCOST_OWN_10	EP_HBURD_OWN_10	EPL_HBURD_OWN_10	F_HBURD_OWN_10	E_HBURD_RENT_10	ET_HOUSINGCOST_RENT_10	EP_HBURD_RENT_10	EPL_HBURD_RENT_10	F_HBURD_RENT_10	E_HBURD_10	ET_HOUSINGCOST_10	EP_HBURD_10	EPL_HBURD_10	F_HBURD_10	E_NOHSDP_10	ET_EDSTATUS_10	EP_NOHSDP_10	EPL_NOHSDP_10	F_NOHSDP_10	E_UNINSUR_12	ET_INSURSTATUS_12	EP_UNINSUR_12	EPL_UNINSUR_12	F_UNINSUR_12	E_AGE65_10	EP_AGE65_10	EPL_AGE65_10	F_AGE65_10	E_AGE17_10	EP_AGE17_10	EPL_AGE17_10	F_AGE17_10	E_DISABL_12	ET_DISABLSTATUS_12	EP_DISABL_12	EPL_DISABL_12	F_DISABL_12	E_SNGPNT_10	ET_FAMILIES_10	EP_SNGPNT_10	EPL_SNGPNT_10	F_SNGPNT_10	E_LIMENG_10	ET_POPAGE5UP_10	EP_LIMENG_10	EPL_LIMENG_10	F_LIMENG_10	E_MINRTY_10	ET_POPETHRACE_10	EP_MINRTY_10	EPL_MINRTY_10	F_MINRTY_10	E_STRHU_10	E_MUNIT_10	EP_MUNIT_10	EPL_MUNIT_10	F_MUNIT_10	E_MOBILE_10	EP_MOBILE_10	EPL_MOBILE_10	E_CROWD_10	ET_OCCUPANTS_10	EP_CROWD_10	EPL_CROWD_10	F_CROWD_10	E_NOVEH_10	ET_KNOWNVEH_10	EP_NOVEH_10	EPL_NOVEH_10	F_NOVEH_10	E_GROUPQ_10	ET_HHTYPE_10	EP_GROUPQ_10	EPL_GROUPQ_10	F_GROUPQ_10	SPL_THEME1_10	RPL_THEME1_10	F_THEME1_10	SPL_THEME2_10	RPL_THEME2_10	F_THEME2_10	SPL_THEME3_10	RPL_THEME3_10	F_THEME3_10	SPL_THEME4_10	RPL_THEME4_10	F_THEME4_10	SPL_THEMES_10	RPL_THEMES_10	F_TOTAL_10	E_TOTPOP_20	E_HU_20	E_HH_20	E_POV150_20	ET_POVSTATUS_20	EP_POV150_20	EPL_POV150_20	F_POV150_20	E_UNEMP_20	ET_EMPSTATUS_20	EP_UNEMP_20	EPL_UNEMP_20	F_UNEMP_20	E_HBURD_OWN_20	ET_HOUSINGCOST_OWN_20	EP_HBURD_OWN_20	EPL_HBURD_OWN_20	F_HBURD_OWN_20	E_HBURD_RENT_20	ET_HOUSINGCOST_RENT_20	EP_HBURD_RENT_20	EPL_HBURD_RENT_20	F_HBURD_RENT_20	E_HBURD_20	ET_HOUSINGCOST_20	EP_HBURD_20	EPL_HBURD_20	F_HBURD_20	E_NOHSDP_20	ET_EDSTATUS_20	EP_NOHSDP_20	EPL_NOHSDP_20	F_NOHSDP_20	E_UNINSUR_20	ET_INSURSTATUS_20	EP_UNINSUR_20	EPL_UNINSUR_20	F_UNINSUR_20	E_AGE65_20	EP_AGE65_20	EPL_AGE65_20	E_AGE17_20	EP_AGE17_20	EPL_AGE17_20	F_AGE17_20	E_DISABL_20	ET_DISABLSTATUS_20	EP_DISABL_20	EPL_DISABL_20	F_DISABL_20	E_SNGPNT_20	ET_FAMILIES_20	EP_SNGPNT_20	EPL_SNGPNT_20	F_SNGPNT_20	E_LIMENG_20	ET_POPAGE5UP_20	EP_LIMENG_20	EPL_LIMENG_20	F_LIMENG_20	E_MINRTY_20	ET_POPETHRACE_20	EP_MINRTY_20	EPL_MINRTY_20	F_MINRTY_20	E_STRHU_20	E_MUNIT_20	EP_MUNIT_20	EPL_MUNIT_20	F_MUNIT_20	E_MOBILE_20	EP_MOBILE_20	EPL_MOBILE_20	E_CROWD_20	ET_OCCUPANTS_20	EP_CROWD_20	EPL_CROWD_20	F_CROWD_20	E_NOVEH_20	ET_KNOWNVEH_20	EP_NOVEH_20	EPL_NOVEH_20	F_NOVEH_20	E_GROUPQ_20	ET_HHTYPE_20	EP_GROUPQ_20	EPL_GROUPQ_20	SPL_THEME1_20	RPL_THEME1_20	F_THEME1_20	SPL_THEME2_20	RPL_THEME2_20	F_THEME2_20	SPL_THEME3_20	RPL_THEME3_20	F_THEME3_20	SPL_THEME4_20	RPL_THEME4_20	F_THEME4_20	SPL_THEMES_20	RPL_THEMES_20	F_TOTAL_20
34001000100	34	001	000100	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2907	1088	983	1127	2907	38.76849	0.8482	1	144	1433	10.048849	0.7544	1	280	435	64.36782	0.9529	1	204	548	37.22628	0.2998	0	484	983	49.23703	0.7813	1	468	1759	26.60603	0.8634	1	532	2543	20.92017	0.8978	1	250	8.599931	0.1777	0	944	32.47334	0.94170	1	186	1851	10.04862	0.2706	0	266	678	39.233038	0.8981	1	177	2611	6.779012	0.7778	1	1928	2907	66.32267	0.7743	1	1088	113	10.386029	0.6229	0	9	0.8272059	0.7223	80	983	8.138352	0.8657	1	265	983	26.95829	0.7354	0	0	2907	0.000000	0.3512	0	4.1451	0.8935	5	3.06590	0.7944	3	0.7743	0.7667	1	3.2975	0.8414	1	11.28280	0.8862	10	2157	941	784	1182	2157	54.79833	0.9571	1	242	1058	22.873346	0.9922	1	215	342	62.86550	0.9780	1	316	442	71.49321	0.9481	1	531	784	67.72959	0.9893	1	396	1274	31.08320	0.9497	1	266	2157	12.331943	0.9041	1	185	8.576727	0.09430	552	25.59110	0.8128	1	297	1605	18.504673	0.74880	0	83	510	16.27451	0.6090	0	251	2020	12.425743	0.8710	1	1852	2157	85.85999	0.8476	1	941	118	12.5398512	0.6385	0	0	0.0000000	0.3216	67	784	8.545918	0.8657	1	212	784	27.04082	0.7502	1	0	2157	0.0000000	0.1517	4.7924	0.9850	5	3.13590	0.8217	2	0.8476	0.8400	1	2.7277	0.6085	2	11.50360	0.9104	10
34001000200	34	001	000200	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3189	2217	1473	519	3189	16.27469	0.4806	0	109	1558	6.996149	0.5179	0	573	955	60.00000	0.9323	1	199	518	38.41699	0.3261	0	772	1473	52.41005	0.8418	1	405	2579	15.70376	0.6491	0	484	3547	13.64533	0.7154	0	847	26.560050	0.9629	1	436	13.67200	0.08181	0	608	3005	20.23295	0.8466	1	42	857	4.900817	0.1204	0	422	3072	13.736979	0.8799	1	1792	3189	56.19316	0.7390	0	2217	901	40.640505	0.8693	1	0	0.0000000	0.3251	48	1473	3.258656	0.7064	0	250	1473	16.97217	0.6444	0	0	3189	0.000000	0.3512	0	3.2048	0.6963	1	2.89161	0.7231	3	0.7390	0.7317	0	2.8964	0.6887	1	9.73181	0.7340	5	3510	2046	1353	1021	3510	29.08832	0.7682	1	121	1852	6.533477	0.6717	0	343	696	49.28161	0.9273	1	416	657	63.31811	0.8696	1	759	1353	56.09756	0.9321	1	553	2338	23.65269	0.8871	1	354	3510	10.085470	0.8530	1	643	18.319088	0.60310	1002	28.54701	0.9055	1	450	2508	17.942584	0.72330	0	237	786	30.15267	0.8539	1	534	3375	15.822222	0.9062	1	2534	3510	72.19373	0.7818	1	2046	906	44.2815249	0.8690	1	0	0.0000000	0.3216	119	1353	8.795270	0.8711	1	324	1353	23.94678	0.7255	0	0	3510	0.0000000	0.1517	4.1121	0.9003	4	3.99200	0.9781	3	0.7818	0.7747	1	2.9389	0.7011	2	11.82480	0.9310	10
34001000300	34	001	000300	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3997	1823	1357	1401	3968	35.30746	0.8164	1	382	2238	17.068811	0.9376	1	176	329	53.49544	0.8855	1	604	1028	58.75486	0.7947	1	780	1357	57.47973	0.9165	1	920	2677	34.36683	0.9346	1	1351	4149	32.56206	0.9811	1	314	7.855892	0.1437	0	937	23.44258	0.55900	0	319	3054	10.44532	0.3000	0	187	782	23.913044	0.7498	0	1080	3671	29.419777	0.9742	1	3357	3997	83.98799	0.8419	1	1823	363	19.912233	0.7535	1	0	0.0000000	0.3251	150	1357	11.053795	0.9136	1	651	1357	47.97347	0.8585	1	0	3997	0.000000	0.3512	0	4.5862	0.9691	5	2.72670	0.6360	1	0.8419	0.8336	1	3.2019	0.8054	3	11.35670	0.8920	10	3801	1640	1226	1857	3801	48.85556	0.9333	1	226	1800	12.555556	0.9267	1	111	280	39.64286	0.8339	1	608	946	64.27061	0.8842	1	719	1226	58.64600	0.9528	1	650	2275	28.57143	0.9337	1	1027	3801	27.019206	0.9914	1	380	9.997369	0.14040	1223	32.17574	0.9607	1	219	2578	8.494957	0.15680	0	268	909	29.48295	0.8456	1	940	3400	27.647059	0.9728	1	3318	3801	87.29282	0.8579	1	1640	262	15.9756098	0.6917	0	0	0.0000000	0.3216	124	1226	10.114192	0.8955	1	477	1226	38.90701	0.8258	1	0	3801	0.0000000	0.1517	4.7379	0.9829	5	3.07630	0.8013	3	0.8579	0.8501	1	2.8863	0.6781	2	11.55840	0.9150	11
34001000400	34	001	000400	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2902	2683	1401	1172	2902	40.38594	0.8615	1	190	1389	13.678906	0.8811	1	364	707	51.48515	0.8627	1	507	694	73.05476	0.9503	1	871	1401	62.16988	0.9572	1	481	1981	24.28067	0.8339	1	674	3204	21.03620	0.8998	1	434	14.955203	0.6083	0	596	20.53756	0.33980	0	426	2607	16.34062	0.6886	0	111	652	17.024540	0.6204	0	215	2736	7.858187	0.8008	1	1792	2902	61.75052	0.7584	1	2683	2049	76.369735	0.9401	1	0	0.0000000	0.3251	69	1401	4.925053	0.7847	1	511	1401	36.47395	0.7992	1	72	2902	2.481048	0.8114	1	4.4335	0.9468	5	3.05790	0.7908	1	0.7584	0.7510	1	3.6605	0.9391	4	11.91030	0.9339	11	3178	2264	1390	1508	3176	47.48111	0.9246	1	172	1804	9.534368	0.8460	1	205	468	43.80342	0.8858	1	622	922	67.46204	0.9192	1	827	1390	59.49640	0.9587	1	364	2076	17.53372	0.8013	1	476	3178	14.977974	0.9390	1	483	15.198238	0.41220	539	16.96035	0.2484	0	319	2639	12.087912	0.38790	0	101	565	17.87611	0.6539	0	583	3022	19.291860	0.9349	1	2186	3178	68.78540	0.7658	1	2264	1609	71.0689046	0.9266	1	15	0.6625442	0.7078	226	1390	16.258993	0.9567	1	599	1390	43.09353	0.8474	1	20	3178	0.6293266	0.6292	4.4696	0.9558	5	2.63730	0.5864	1	0.7658	0.7588	1	4.0677	0.9762	3	11.94040	0.9387	10
34001000500	34	001	000500	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3483	1241	1027	1938	3483	55.64169	0.9533	1	124	1630	7.607362	0.5830	0	227	446	50.89686	0.8549	1	478	581	82.27194	0.9799	1	705	1027	68.64654	0.9863	1	733	2077	35.29129	0.9396	1	727	3258	22.31430	0.9149	1	377	10.824002	0.3081	0	1055	30.28998	0.90140	1	268	2401	11.16202	0.3549	0	209	763	27.391874	0.7940	1	911	3077	29.606760	0.9746	1	3036	3483	87.16624	0.8550	1	1241	52	4.190169	0.4505	0	4	0.3223207	0.6567	113	1027	11.002921	0.9128	1	422	1027	41.09056	0.8250	1	0	3483	0.000000	0.3512	0	4.3771	0.9379	4	3.33300	0.8766	3	0.8550	0.8467	1	3.1962	0.8026	2	11.76130	0.9229	10	3385	1185	945	1682	3364	50.00000	0.9391	1	72	1577	4.565631	0.4586	0	185	468	39.52991	0.8332	1	362	477	75.89099	0.9703	1	547	945	57.88360	0.9477	1	592	1983	29.85376	0.9422	1	738	3385	21.802068	0.9817	1	240	7.090103	0.05988	1129	33.35303	0.9689	1	135	2256	5.984043	0.04817	0	110	717	15.34170	0.5822	0	721	3076	23.439532	0.9569	1	3029	3385	89.48301	0.8727	1	1185	9	0.7594937	0.2382	0	0	0.0000000	0.3216	103	945	10.899471	0.9072	1	263	945	27.83069	0.7560	1	0	3385	0.0000000	0.1517	4.2693	0.9283	4	2.61605	0.5709	2	0.8727	0.8648	1	2.3747	0.4357	2	10.13275	0.7921	9
34001001100	34	001	001100	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2204	1204	1204	1185	2204	53.76588	0.9457	1	219	927	23.624596	0.9830	1	97	172	56.39535	0.9094	1	462	1032	44.76744	0.4746	0	559	1204	46.42857	0.7197	0	346	1440	24.02778	0.8306	1	469	1942	24.15036	0.9360	1	363	16.470054	0.7020	0	578	26.22505	0.74410	0	442	1558	28.36970	0.9675	1	247	396	62.373737	0.9898	1	104	2051	5.070697	0.7260	0	2118	2204	96.09800	0.9204	1	1204	570	47.342193	0.8858	1	0	0.0000000	0.3251	14	1204	1.162791	0.4877	0	817	1204	67.85714	0.9413	1	0	2204	0.000000	0.3512	0	4.4150	0.9451	4	4.12940	0.9805	2	0.9204	0.9114	1	2.9911	0.7243	2	12.45590	0.9597	9	1950	1267	1096	1131	1950	58.00000	0.9678	1	66	706	9.348442	0.8395	1	42	101	41.58416	0.8612	1	309	995	31.05528	0.1959	0	351	1096	32.02555	0.4782	0	510	1379	36.98332	0.9763	1	155	1950	7.948718	0.7660	1	392	20.102564	0.69880	447	22.92308	0.6712	0	570	1503	37.924152	0.99200	1	143	374	38.23529	0.9167	1	109	1841	5.920695	0.7464	0	1909	1950	97.89744	0.9529	1	1267	479	37.8058406	0.8464	1	0	0.0000000	0.3216	33	1096	3.010949	0.6446	0	743	1096	67.79197	0.9414	1	0	1950	0.0000000	0.1517	4.0278	0.8848	4	4.02510	0.9798	2	0.9529	0.9442	1	2.9057	0.6869	2	11.91150	0.9365	9

Code

# Find tracts with divisional data in both 2010 and 2020
svi_national <- merge_svi_data(svi_2010_national, svi_2020_national)
svi_national %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID_2010_trt	FIPS_st	FIPS_county	FIPS_tract	state	state_name	county	region_number	region	division_number	division	E_TOTPOP_10	E_HU_10	E_HH_10	E_POV150_10	ET_POVSTATUS_10	EP_POV150_10	EPL_POV150_10	E_UNEMP_10	ET_EMPSTATUS_10	EP_UNEMP_10	EPL_UNEMP_10	E_HBURD_OWN_10	ET_HOUSINGCOST_OWN_10	EP_HBURD_OWN_10	EPL_HBURD_OWN_10	E_HBURD_RENT_10	ET_HOUSINGCOST_RENT_10	EP_HBURD_RENT_10	EPL_HBURD_RENT_10	E_HBURD_10	ET_HOUSINGCOST_10	EP_HBURD_10	EPL_HBURD_10	E_NOHSDP_10	ET_EDSTATUS_10	EP_NOHSDP_10	EPL_NOHSDP_10	F_NOHSDP_10	E_UNINSUR_12	ET_INSURSTATUS_12	EP_UNINSUR_12	EPL_UNINSUR_12	E_AGE65_10	EP_AGE65_10	EPL_AGE65_10	F_AGE65_10	E_AGE17_10	EP_AGE17_10	EPL_AGE17_10	F_AGE17_10	E_DISABL_12	ET_DISABLSTATUS_12	EP_DISABL_12	EPL_DISABL_12	F_DISABL_12	E_SNGPNT_10	ET_FAMILIES_10	EP_SNGPNT_10	EPL_SNGPNT_10	F_SNGPNT_10	E_LIMENG_10	ET_POPAGE5UP_10	EP_LIMENG_10	EPL_LIMENG_10	E_MINRTY_10	ET_POPETHRACE_10	EP_MINRTY_10	EPL_MINRTY_10	F_MINRTY_10	E_STRHU_10	E_MUNIT_10	EP_MUNIT_10	EPL_MUNIT_10	E_MOBILE_10	EP_MOBILE_10	EPL_MOBILE_10	F_MOBILE_10	E_CROWD_10	ET_OCCUPANTS_10	EP_CROWD_10	EPL_CROWD_10	E_NOVEH_10	ET_KNOWNVEH_10	EP_NOVEH_10	EPL_NOVEH_10	F_NOVEH_10	ET_HHTYPE_10	EPL_GROUPQ_10	SPL_THEME1_10	RPL_THEME1_10	F_THEME1_10	SPL_THEME2_10	RPL_THEME2_10	F_THEME2_10	SPL_THEME3_10	RPL_THEME3_10	F_THEME3_10	SPL_THEME4_10	RPL_THEME4_10	F_THEME4_10	SPL_THEMES_10	RPL_THEMES_10	F_TOTAL_10	E_TOTPOP_20	E_HU_20	E_HH_20	E_POV150_20	ET_POVSTATUS_20	EP_POV150_20	EPL_POV150_20	F_POV150_20	E_UNEMP_20	ET_EMPSTATUS_20	EP_UNEMP_20	EPL_UNEMP_20	E_HBURD_OWN_20	ET_HOUSINGCOST_OWN_20	EP_HBURD_OWN_20	EPL_HBURD_OWN_20	F_HBURD_OWN_20	E_HBURD_RENT_20	ET_HOUSINGCOST_RENT_20	EP_HBURD_RENT_20	EPL_HBURD_RENT_20	F_HBURD_RENT_20	E_HBURD_20	ET_HOUSINGCOST_20	EP_HBURD_20	EPL_HBURD_20	E_NOHSDP_20	ET_EDSTATUS_20	EP_NOHSDP_20	EPL_NOHSDP_20	E_UNINSUR_20	ET_INSURSTATUS_20	EP_UNINSUR_20	EPL_UNINSUR_20	F_UNINSUR_20	E_AGE65_20	EP_AGE65_20	EPL_AGE65_20	F_AGE65_20	E_AGE17_20	EP_AGE17_20	EPL_AGE17_20	F_AGE17_20	E_DISABL_20	ET_DISABLSTATUS_20	EP_DISABL_20	EPL_DISABL_20	F_DISABL_20	E_SNGPNT_20	ET_FAMILIES_20	EP_SNGPNT_20	EPL_SNGPNT_20	F_SNGPNT_20	E_LIMENG_20	ET_POPAGE5UP_20	EP_LIMENG_20	EPL_LIMENG_20	E_MINRTY_20	ET_POPETHRACE_20	EP_MINRTY_20	EPL_MINRTY_20	F_MINRTY_20	E_STRHU_20	E_MUNIT_20	EP_MUNIT_20	EPL_MUNIT_20	E_MOBILE_20	EP_MOBILE_20	EPL_MOBILE_20	F_MOBILE_20	E_CROWD_20	ET_OCCUPANTS_20	EP_CROWD_20	EPL_CROWD_20	E_NOVEH_20	ET_KNOWNVEH_20	EP_NOVEH_20	EPL_NOVEH_20	E_GROUPQ_20	ET_HHTYPE_20	EP_GROUPQ_20	EPL_GROUPQ_20	F_GROUPQ_20	SPL_THEME1_20	RPL_THEME1_20	F_THEME1_20	SPL_THEME2_20	RPL_THEME2_20	F_THEME2_20	SPL_THEME3_20	RPL_THEME3_20	F_THEME3_20	SPL_THEME4_20	RPL_THEME4_20	F_THEME4_20	SPL_THEMES_20	RPL_THEMES_20	F_TOTAL_20
01001020100	01	001	020100	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	1809	771	696	297	1809	16.41791	0.3871	36	889	4.049494	0.1790	127	598	21.23746	0.20770	47	98	47.95918	0.5767	174	696	25.00000	0.18790	196	1242	15.780998	0.6093	0	186	1759	10.574190	0.3790	222	12.271973	0.4876	0	445	24.59923	0.5473	0	298	1335	22.32210	0.8454	1	27	545	4.954128	0.09275	0	36	1705	2.1114370	0.59040	385	1809	21.282477	0.4524	0	771	0	0.0000000	0.1224	92	11.9325551	0.8005	1	0	696	0.0000000	0.1238	50	696	7.183908	0.6134	0	1809	0.364	1.74230	0.28200	0	2.56345	0.5296	1	0.4524	0.4482	0	2.0241	0.2519	1	6.78225	0.3278	2	1941	710	693	352	1941	18.13498	0.4630	0	18	852	2.112676	0.15070	81	507	15.976331	0.26320	0	63	186	33.87097	0.2913	0	144	693	20.77922	0.2230	187	1309	14.285714	0.6928	187	1941	9.634209	0.6617	0	295	15.19835	0.4601	0	415	21.38073	0.4681	0	391	1526	25.62254	0.9011	1	58	555	10.45045	0.3451	0	0	1843	0.0000000	0.09479	437	1941	22.51417	0.3902	0	710	0	0.0000000	0.1079	88	12.3943662	0.8263	1	0	693	0.0000000	0.09796	10	693	1.443001	0.1643	0	1941	0.000000	0.1831	0	2.19120	0.4084	0	2.26919	0.3503	1	0.3902	0.3869	0	1.37956	0.07216	1	6.23015	0.2314	2
01001020200	01	001	020200	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	2020	816	730	495	1992	24.84940	0.5954	68	834	8.153477	0.5754	49	439	11.16173	0.02067	105	291	36.08247	0.3019	154	730	21.09589	0.09312	339	1265	26.798419	0.8392	1	313	2012	15.556660	0.6000	204	10.099010	0.3419	0	597	29.55446	0.8192	1	359	1515	23.69637	0.8791	1	132	456	28.947368	0.83510	1	15	1890	0.7936508	0.40130	1243	2020	61.534653	0.7781	1	816	0	0.0000000	0.1224	34	4.1666667	0.6664	0	13	730	1.7808219	0.5406	115	730	15.753425	0.8382	1	2020	0.364	2.70312	0.56650	1	3.27660	0.8614	3	0.7781	0.7709	1	2.5316	0.5047	1	9.28942	0.6832	6	1757	720	573	384	1511	25.41363	0.6427	0	29	717	4.044630	0.41320	33	392	8.418367	0.03542	0	116	181	64.08840	0.9086	1	149	573	26.00349	0.4041	139	1313	10.586443	0.5601	91	1533	5.936073	0.4343	0	284	16.16392	0.5169	0	325	18.49744	0.2851	0	164	1208	13.57616	0.4127	0	42	359	11.69916	0.3998	0	0	1651	0.0000000	0.09479	1116	1757	63.51736	0.7591	1	720	3	0.4166667	0.2470	5	0.6944444	0.5106	0	9	573	1.5706806	0.46880	57	573	9.947644	0.7317	212	1757	12.066022	0.9549	1	2.45440	0.4888	0	1.70929	0.1025	0	0.7591	0.7527	1	2.91300	0.68620	1	7.83579	0.4802	2
01001020300	01	001	020300	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	3543	1403	1287	656	3533	18.56779	0.4443	93	1552	5.992268	0.3724	273	957	28.52665	0.45780	178	330	53.93939	0.7152	451	1287	35.04274	0.49930	346	2260	15.309734	0.5950	0	252	3102	8.123791	0.2596	487	13.745413	0.5868	0	998	28.16822	0.7606	1	371	2224	16.68165	0.6266	0	126	913	13.800657	0.46350	0	0	3365	0.0000000	0.09298	637	3543	17.979114	0.4049	0	1403	10	0.7127584	0.3015	2	0.1425517	0.4407	0	0	1287	0.0000000	0.1238	101	1287	7.847708	0.6443	0	3543	0.364	2.17060	0.41010	0	2.53048	0.5116	1	0.4049	0.4011	0	1.8743	0.1942	0	6.98028	0.3576	1	3694	1464	1351	842	3694	22.79372	0.5833	0	53	1994	2.657974	0.22050	117	967	12.099276	0.11370	0	147	384	38.28125	0.3856	0	264	1351	19.54108	0.1827	317	2477	12.797739	0.6460	127	3673	3.457664	0.2308	0	464	12.56091	0.3088	0	929	25.14889	0.7080	0	473	2744	17.23761	0.6211	0	263	975	26.97436	0.8234	1	128	3586	3.5694367	0.70770	1331	3694	36.03140	0.5515	0	1464	26	1.7759563	0.3675	14	0.9562842	0.5389	0	35	1351	2.5906736	0.60550	42	1351	3.108808	0.3415	0	3694	0.000000	0.1831	0	1.86330	0.3063	0	3.16900	0.8380	1	0.5515	0.5468	0	2.03650	0.26830	0	7.62030	0.4460	1
01001020400	01	001	020400	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	4840	1957	1839	501	4840	10.35124	0.2177	101	2129	4.744011	0.2447	310	1549	20.01291	0.17080	89	290	30.68966	0.2044	399	1839	21.69657	0.10540	274	3280	8.353658	0.3205	0	399	4293	9.294200	0.3171	955	19.731405	0.8643	1	1195	24.69008	0.5530	0	625	3328	18.78005	0.7233	0	152	1374	11.062591	0.34710	0	10	4537	0.2204100	0.22560	297	4840	6.136364	0.1647	0	1957	33	1.6862545	0.3843	25	1.2774655	0.5516	0	14	1839	0.7612833	0.3564	19	1839	1.033170	0.1127	0	4840	0.364	1.20540	0.13470	0	2.71330	0.6129	1	0.1647	0.1632	0	1.7690	0.1591	0	5.85240	0.1954	1	3539	1741	1636	503	3539	14.21305	0.3472	0	39	1658	2.352232	0.17990	219	1290	16.976744	0.30880	0	74	346	21.38728	0.1037	0	293	1636	17.90954	0.1333	173	2775	6.234234	0.3351	169	3529	4.788892	0.3448	0	969	27.38062	0.9225	1	510	14.41085	0.1208	0	670	3019	22.19278	0.8194	1	148	1137	13.01671	0.4541	0	89	3409	2.6107363	0.64690	454	3539	12.82848	0.2364	0	1741	143	8.2136703	0.6028	0	0.0000000	0.2186	0	10	1636	0.6112469	0.28340	72	1636	4.400978	0.4538	0	3539	0.000000	0.1831	0	1.34030	0.1575	0	2.96370	0.7496	2	0.2364	0.2344	0	1.74170	0.16270	0	6.28210	0.2389	2
01001020500	01	001	020500	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	9938	3969	3741	1096	9938	11.02838	0.2364	188	4937	3.807981	0.1577	426	2406	17.70574	0.11050	528	1335	39.55056	0.3753	954	3741	25.50120	0.20140	293	5983	4.897209	0.1655	0	740	10110	7.319486	0.2211	837	8.422218	0.2408	0	3012	30.30791	0.8455	1	759	7155	10.60797	0.2668	0	476	2529	18.821669	0.63540	0	78	9297	0.8389803	0.41110	1970	9938	19.822902	0.4330	0	3969	306	7.7097506	0.6153	0	0.0000000	0.2198	0	7	3741	0.1871157	0.2535	223	3741	5.960973	0.5483	0	9938	0.364	0.98210	0.08468	0	2.39960	0.4381	1	0.4330	0.4290	0	2.0009	0.2430	0	5.81560	0.1905	1	10674	4504	4424	1626	10509	15.47245	0.3851	0	81	5048	1.604596	0.09431	321	2299	13.962592	0.17970	0	711	2125	33.45882	0.2836	0	1032	4424	23.32731	0.3109	531	6816	7.790493	0.4251	301	10046	2.996217	0.1894	0	1613	15.11149	0.4553	0	2765	25.90407	0.7494	0	1124	7281	15.43744	0.5253	0	342	2912	11.74451	0.4019	0	52	9920	0.5241935	0.35230	2603	10674	24.38636	0.4160	0	4504	703	15.6083481	0.7378	29	0.6438721	0.5037	0	37	4424	0.8363472	0.33420	207	4424	4.679023	0.4754	176	10674	1.648866	0.7598	1	1.40481	0.1743	0	2.48420	0.4802	0	0.4160	0.4125	0	2.81090	0.63730	1	7.11591	0.3654	1
01001020600	01	001	020600	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	3402	1456	1308	735	3402	21.60494	0.5199	134	1720	7.790698	0.5436	242	1032	23.44961	0.28010	62	276	22.46377	0.1035	304	1308	23.24159	0.14070	301	2151	13.993491	0.5510	0	355	3445	10.304790	0.3656	386	11.346267	0.4232	0	931	27.36626	0.7200	0	440	2439	18.04018	0.6912	0	143	924	15.476190	0.52900	0	4	3254	0.1229256	0.19840	723	3402	21.252205	0.4519	0	1456	18	1.2362637	0.3507	433	29.7390110	0.9468	1	16	1308	1.2232416	0.4493	28	1308	2.140673	0.2298	0	3402	0.364	2.12080	0.39510	0	2.56180	0.5288	0	0.4519	0.4477	0	2.3406	0.4048	1	7.47510	0.4314	1	3536	1464	1330	1279	3523	36.30429	0.8215	1	34	1223	2.780049	0.23780	321	1111	28.892889	0.75870	1	67	219	30.59361	0.2305	0	388	1330	29.17293	0.5075	306	2380	12.857143	0.6480	415	3496	11.870709	0.7535	1	547	15.46946	0.4760	0	982	27.77149	0.8327	1	729	2514	28.99761	0.9488	1	95	880	10.79545	0.3601	0	0	3394	0.0000000	0.09479	985	3536	27.85633	0.4608	0	1464	0	0.0000000	0.1079	364	24.8633880	0.9300	1	0	1330	0.0000000	0.09796	17	1330	1.278196	0.1463	0	3536	0.000000	0.1831	0	2.96830	0.6434	2	2.71239	0.6156	2	0.4608	0.4569	0	1.46526	0.08976	1	7.60675	0.4440	5

NMTC Data Wrangling

Now let’s process our NMTC data. We will begin by exploring the details of our data sets:

Code

colnames(orig_nmtc)

 [1] "2010 Census Tract Number FIPS code. GEOID"                                                   
 [2] "OMB Metro/Non-metro Designation, July 2015 (OMB 15-01)"                                      
 [3] "Does Census Tract Qualify For NMTC Low-Income Community (LIC) on Poverty or Income Criteria?"
 [4] "Census Tract Poverty Rate % (2011-2015 ACS)"                                                 
 [5] "Does Census Tract Qualify on Poverty Criteria>=20%?"                                         
 [6] "Census Tract Percent of Benchmarked Median Family Income (%) 2011-2015 ACS"                  
 [7] "Does Census Tract Qualify on Median Family Income Criteria<=80%?"                            
 [8] "Census Tract Unemployment Rate (%) 2011-2015"                                                
 [9] "County Code"                                                                                 
[10] "State Abbreviation"                                                                          
[11] "State Name"                                                                                  
[12] "County Name"                                                                                 
[13] "Census Tract Unemployment to National Unemployment Ratio"                                    
[14] "Is Tract Unemployment to National Unemployment Ratio >1.5?"                                  
[15] "Population for whom poverty status is determined 2011-2015 ACS"

Let’s rename a few columns to make them easier for processing:

Code

orig_nmtc_df <- orig_nmtc %>% 
  rename("GEOID10" = "2010 Census Tract Number FIPS code. GEOID",
         "nmtc_eligibility_orig" = "Does Census Tract Qualify For NMTC Low-Income Community (LIC) on Poverty or Income Criteria?")

orig_nmtc_df %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID10	OMB Metro/Non-metro Designation, July 2015 (OMB 15-01)	nmtc_eligibility_orig	Census Tract Poverty Rate % (2011-2015 ACS)	Does Census Tract Qualify on Poverty Criteria>=20%?	Census Tract Percent of Benchmarked Median Family Income (%) 2011-2015 ACS	Does Census Tract Qualify on Median Family Income Criteria<=80%?	Census Tract Unemployment Rate (%) 2011-2015	County Code	State Abbreviation	State Name	County Name	Census Tract Unemployment to National Unemployment Ratio	Is Tract Unemployment to National Unemployment Ratio >1.5?	Population for whom poverty status is determined 2011-2015 ACS
01001020100	Metropolitan	No	8.1	No	122.930646878856	No	5.4	01001	AL	Alabama	Autauga	0.6506024096385542	No	1948
01001020200	Metropolitan	Yes	25.5	Yes	82.402258244451573	No	13.3	01001	AL	Alabama	Autauga	1.6024096385542168	Yes	1983
01001020300	Metropolitan	No	12.7	No	94.261422220719723	No	6.2	01001	AL	Alabama	Autauga	0.74698795180722888	No	2968
01001020400	Metropolitan	No	2.1	No	116.82358310373388	No	10.8	01001	AL	Alabama	Autauga	1.3012048192771084	No	4423
01001020500	Metropolitan	No	11.4	No	127.74293876033198	No	4.2	01001	AL	Alabama	Autauga	0.50602409638554213	No	10563
01001020600	Metropolitan	No	14.4	No	111.98255607579317	No	10.9	01001	AL	Alabama	Autauga	1.3132530120481927	No	3851

We also have additional census tracts that have been deemed eligible for the program due to high migration:

Code

colnames(high_migration_nmtc)

[1] "2010 Census Tract Number FIPS code GEOID"                                  
[2] "20-year County population loss 1990-2010 census"                           
[3] "% Median Family Income (MFI) / Area Income 2011-2015 (between 80%-85% MFI)"

We will also rename the GEOID column in this data set:

Code

high_migration_nmtc_df <- high_migration_nmtc %>% rename("GEOID10" = "2010 Census Tract Number FIPS code GEOID")

high_migration_nmtc_df %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID10	20-year County population loss 1990-2010 census	% Median Family Income (MFI) / Area Income 2011-2015 (between 80%-85% MFI)
01087231601	-0.1394416	82.06754
05039970300	-0.1558144	84.78236
08017960600	-0.2340426	84.36239
17067953800	-0.1061620	80.36788
17067954200	-0.1061620	84.48551
17067954300	-0.1061620	84.44497

If we look back at our original data set, we can see that it doesn’t have the census tracts in the high migration data set coded as being eligible for the NMTC since eligibility for these tracts were added at a later date. See below as an example:

Code

# See original doesn't have high migration tracts coded as eligible
orig_nmtc_df %>% filter(GEOID10 == "01087231601") %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID10	OMB Metro/Non-metro Designation, July 2015 (OMB 15-01)	nmtc_eligibility_orig	Census Tract Poverty Rate % (2011-2015 ACS)	Does Census Tract Qualify on Poverty Criteria>=20%?	Census Tract Percent of Benchmarked Median Family Income (%) 2011-2015 ACS	Does Census Tract Qualify on Median Family Income Criteria<=80%?	Census Tract Unemployment Rate (%) 2011-2015	County Code	State Abbreviation	State Name	County Name	Census Tract Unemployment to National Unemployment Ratio	Is Tract Unemployment to National Unemployment Ratio >1.5?	Population for whom poverty status is determined 2011-2015 ACS
01087231601	Non-Metropolitan	No	16.2	No	82.067544858242542	No	11.3	01087	AL	Alabama	Macon	1.3614457831325302	No	888

In order to address this, we need to update eligibility in our original data set for the census tracts in the high migration of data set:

Code

# Add column to label tracts as high migration
high_migration_nmtc_df <- high_migration_nmtc_df %>% mutate(high_migration = "Yes")

# Join to original column
orig_nmtc_df <- left_join(orig_nmtc_df, high_migration_nmtc_df, join_by(GEOID10 == GEOID10))

# Update eligibility column with coalesce()
nmtc_df <- orig_nmtc_df %>% 
  mutate(nmtc_eligibility = coalesce(high_migration, nmtc_eligibility_orig))

nmtc_df %>% filter(GEOID10 == "01087231601") %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID10	OMB Metro/Non-metro Designation, July 2015 (OMB 15-01)	nmtc_eligibility_orig	Census Tract Poverty Rate % (2011-2015 ACS)	Does Census Tract Qualify on Poverty Criteria>=20%?	Census Tract Percent of Benchmarked Median Family Income (%) 2011-2015 ACS	Does Census Tract Qualify on Median Family Income Criteria<=80%?	Census Tract Unemployment Rate (%) 2011-2015	County Code	State Abbreviation	State Name	County Name	Census Tract Unemployment to National Unemployment Ratio	Is Tract Unemployment to National Unemployment Ratio >1.5?	Population for whom poverty status is determined 2011-2015 ACS	20-year County population loss 1990-2010 census	% Median Family Income (MFI) / Area Income 2011-2015 (between 80%-85% MFI)	high_migration	nmtc_eligibility
01087231601	Non-Metropolitan	No	16.2	No	82.067544858242542	No	11.3	01087	AL	Alabama	Macon	1.3614457831325302	No	888	-0.1394416	82.06754	Yes	Yes

Create a data set only of our NMTC eligible census tracts:

Code

nmtc_eligible <- nmtc_df %>% 
  select(GEOID10, nmtc_eligibility, `County Code`, `County Name`, `State Abbreviation`, `State Name`) %>% 
  filter(tolower(nmtc_eligibility) == "yes")

nmtc_eligible %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID10	nmtc_eligibility	County Code	County Name	State Abbreviation	State Name
01001020200	Yes	01001	Autauga	AL	Alabama
01001020700	Yes	01001	Autauga	AL	Alabama
01001021100	Yes	01001	Autauga	AL	Alabama
01003010200	Yes	01003	Baldwin	AL	Alabama
01003010500	Yes	01003	Baldwin	AL	Alabama
01003010600	Yes	01003	Baldwin	AL	Alabama

To merge to our SVI data, we only need the eligibility flag and the GEOID so we will limit our data set to these columns:

Code

# Save just tract ID and eligibility
nmtc_eligible_df <- nmtc_eligible %>% select(GEOID10, nmtc_eligibility)
nmtc_eligible_df %>% head()

# A tibble: 6 × 2
  GEOID10     nmtc_eligibility
  <chr>       <chr>           
1 01001020200 Yes             
2 01001020700 Yes             
3 01001021100 Yes             
4 01003010200 Yes             
5 01003010500 Yes             
6 01003010600 Yes

Now let’s look at our NMTC award data:

Code

nmtc_awards_data %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

Project ID	2010 Census Tract	Metro/Non-Metro, 2010 Census	Origination Year	Community Development Entity (CDE) Name	Project QLICI Amount	Estimated Total Project Cost	City	State	Zip Code	QALICB Type	Multi-CDE	Multi-Tract Project
AK0001	2070000100	Non-Metropolitan	2008	Alaska Growth Capital BIDCO, Inc.	300000	300000	Aleknagik	Alaska	99555	NRE	NO	NO
AK0002	2020001000	Metropolitan	2006	Alaska Growth Capital BIDCO, Inc.	1008750	1345000	Anchorage	Alaska	99501	NRE	NO	NO
AK0003	2020000600	Metropolitan	2006	HEDC New Markets, Inc	5061506	8694457	Anchorage	Alaska	99508	NRE	NO	NO
AK0004	2020001000	Metropolitan	2006	Alaska Growth Capital BIDCO, Inc.	187500	250000	Anchorage	Alaska	99501	NRE	NO	NO
AK0006	2020001802	Metropolitan	2006	Alaska Growth Capital BIDCO, Inc.	750000	1180000	Anchorage	Alaska	99507	NRE	NO	NO
AK0007	2020001900	Metropolitan	2006	Alaska Growth Capital BIDCO, Inc.	127500	150000	Anchorage	Alaska	99503	NRE	NO	NO

Here we can see that our 2010 Census Tract column is missing leading zeroes. We need to fix this to allow for joining with our SVI data. To do this, we can pad our census tract data column to 11 to ensure that the leading zeroes are added back:

Code

nmtc_awards <- nmtc_awards_data %>% 
  mutate(`2010 Census Tract` = str_pad(`2010 Census Tract`, 11, "left", pad=0)) %>%
  rename("GEOID10" =`2010 Census Tract`)

nmtc_awards %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

Project ID	GEOID10	Metro/Non-Metro, 2010 Census	Origination Year	Community Development Entity (CDE) Name	Project QLICI Amount	Estimated Total Project Cost	City	State	Zip Code	QALICB Type	Multi-CDE	Multi-Tract Project
AK0001	02070000100	Non-Metropolitan	2008	Alaska Growth Capital BIDCO, Inc.	300000	300000	Aleknagik	Alaska	99555	NRE	NO	NO
AK0002	02020001000	Metropolitan	2006	Alaska Growth Capital BIDCO, Inc.	1008750	1345000	Anchorage	Alaska	99501	NRE	NO	NO
AK0003	02020000600	Metropolitan	2006	HEDC New Markets, Inc	5061506	8694457	Anchorage	Alaska	99508	NRE	NO	NO
AK0004	02020001000	Metropolitan	2006	Alaska Growth Capital BIDCO, Inc.	187500	250000	Anchorage	Alaska	99501	NRE	NO	NO
AK0006	02020001802	Metropolitan	2006	Alaska Growth Capital BIDCO, Inc.	750000	1180000	Anchorage	Alaska	99507	NRE	NO	NO
AK0007	02020001900	Metropolitan	2006	Alaska Growth Capital BIDCO, Inc.	127500	150000	Anchorage	Alaska	99503	NRE	NO	NO

Code

# Create character zip_code column:
nmtc_awards <- nmtc_awards %>% 
  mutate(zip_code = str_pad(`Zip Code`, 5, "left", pad=0))

nmtc_awards %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

Project ID	GEOID10	Metro/Non-Metro, 2010 Census	Origination Year	Community Development Entity (CDE) Name	Project QLICI Amount	Estimated Total Project Cost	City	State	Zip Code	QALICB Type	Multi-CDE	Multi-Tract Project	zip_code
AK0001	02070000100	Non-Metropolitan	2008	Alaska Growth Capital BIDCO, Inc.	300000	300000	Aleknagik	Alaska	99555	NRE	NO	NO	99555
AK0002	02020001000	Metropolitan	2006	Alaska Growth Capital BIDCO, Inc.	1008750	1345000	Anchorage	Alaska	99501	NRE	NO	NO	99501
AK0003	02020000600	Metropolitan	2006	HEDC New Markets, Inc	5061506	8694457	Anchorage	Alaska	99508	NRE	NO	NO	99508
AK0004	02020001000	Metropolitan	2006	Alaska Growth Capital BIDCO, Inc.	187500	250000	Anchorage	Alaska	99501	NRE	NO	NO	99501
AK0006	02020001802	Metropolitan	2006	Alaska Growth Capital BIDCO, Inc.	750000	1180000	Anchorage	Alaska	99507	NRE	NO	NO	99507
AK0007	02020001900	Metropolitan	2006	Alaska Growth Capital BIDCO, Inc.	127500	150000	Anchorage	Alaska	99503	NRE	NO	NO	99503

Now that we have our awards data formatted, we can view the years of data before 2010:

Code

# View years
nmtc_awards_data %>% 
  filter(`Origination Year` <= 2010)  %>% 
  select(`Origination Year`) %>% 
  unique()

# A tibble: 10 × 1
   `Origination Year`
                <dbl>
 1               2008
 2               2006
 3               2007
 4               2009
 5               2010
 6               2004
 7               2003
 8               2005
 9               2002
10               2001

Now let’s find the number of projects in each tract before 2010:

Code

# View tracts
nmtc_awards_pre2010 <- nmtc_awards %>% 
  filter(`Origination Year` <= 2010) %>% 
  count(GEOID10) %>% 
  rename("pre10_nmtc_project_cnt" = "n")

nmtc_awards_dollars_pre2010 <- nmtc_awards %>% 
  filter(`Origination Year` <= 2010) %>% 
  group_by(GEOID10) %>% 
  summarise(pre10_nmtc_dollars = sum(`Project QLICI Amount`, na.rm = TRUE))

nmtc_awards_pre2010 <- left_join(nmtc_awards_pre2010, 
                                 nmtc_awards_dollars_pre2010, 
                                 join_by(GEOID10 == GEOID10))

nmtc_awards_pre2010$pre10_nmtc_dollars_formatted <- scales::dollar_format()(nmtc_awards_pre2010$pre10_nmtc_dollars)

nmtc_awards_pre2010 %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID10	pre10_nmtc_project_cnt	pre10_nmtc_dollars	pre10_nmtc_dollars_formatted
01059973500	1	5000000	$5,000,000
01069041400	1	2500000	$2,500,000
01073001902	1	14400000	$14,400,000
01073002700	1	1000000	$1,000,000
01073004200	1	5908129	$5,908,129
01073004500	3	37950000	$37,950,000

Let’s view the years after 2010:

Code

# View years
nmtc_awards_data %>% 
  filter(`Origination Year` > 2010)  %>% 
  select(`Origination Year`) %>% 
  unique()

# A tibble: 11 × 1
   `Origination Year`
                <dbl>
 1               2011
 2               2012
 3               2017
 4               2013
 5               2014
 6               2016
 7               2015
 8               2018
 9               2019
10               2020
11               2021

Now let’s view what states have data for years 2011-2020 and we can see we have all 50 and D.C.:

Code

nmtc_awards_data %>% 
  filter(`Origination Year` > 2010 & `Origination Year` <= 2020) %>% 
  select(State) %>% 
  filter(!State %in% c("American Samoa", "Guam", "Puerto Rico")) %>% 
  unique() %>% 
  mutate(n = row_number()) %>% 
  kbl() %>% kable_styling() %>% scroll_box(width = "100%")

State	n
Alaska	1
Alabama	2
Arkansas	3
Arizona	4
California	5
Oregon	6
Colorado	7
Connecticut	8
Delaware	9
District of Columbia	10
Florida	11
Illinois	12
Georgia	13
Oklahoma	14
Hawaii	15
Iowa	16
Idaho	17
Missouri	18
New York	19
Indiana	20
Kansas	21
Kentucky	22
Louisiana	23
Massachusetts	24
New Jersey	25
Maryland	26
Maine	27
Michigan	28
Minnesota	29
Mississippi	30
Montana	31
North Carolina	32
North Dakota	33
Nebraska	34
New Hampshire	35
New Mexico	36
Nevada	37
Ohio	38
Pennsylvania	39
Rhode Island	40
South Carolina	41
South Dakota	42
Tennessee	43
Texas	44
Utah	45
Virginia	46
Vermont	47
Washington	48
Wisconsin	49
West Virginia	50
Wyoming	51

Code

nmtc_awards_post2010 <- nmtc_awards %>% 
  filter(`Origination Year` > 2010 & `Origination Year` <= 2020) %>% 
  count(GEOID10) %>% 
  rename("post10_nmtc_project_cnt" = "n")

nmtc_awards_dollars_post2010 <- nmtc_awards %>% 
  filter(`Origination Year` > 2010 & `Origination Year` <= 2020) %>% 
  group_by(GEOID10) %>% 
  summarise(post10_nmtc_dollars = sum(`Project QLICI Amount`, na.rm = TRUE))

nmtc_awards_post2010 <- left_join(nmtc_awards_post2010, 
                                  nmtc_awards_dollars_post2010, 
                                  join_by(GEOID10 == GEOID10))

nmtc_awards_post2010$post10_nmtc_dollars_formatted <- scales::dollar_format()(nmtc_awards_post2010$post10_nmtc_dollars)

nmtc_awards_post2010 %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID10	post10_nmtc_project_cnt	post10_nmtc_dollars	post10_nmtc_dollars_formatted
0000000000.	3	24200000	$24,200,000
01003010200	1	408000	$408,000
01003010300	1	9880000	$9,880,000
01003010600	1	8000000	$8,000,000
01003010904	1	22460000	$22,460,000
01003011501	6	37147460	$37,147,460

SVI Data

Now that all of our SVI data is loaded, we can merge the NMTC data with our SVI data:

Code

# Divisional data
svi_divisional %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID_2010_trt	FIPS_st	FIPS_county	FIPS_tract	state	state_name	county	region_number	region	division_number	division	E_TOTPOP_10	E_HU_10	E_HH_10	E_POV150_10	ET_POVSTATUS_10	EP_POV150_10	EPL_POV150_10	F_POV150_10	E_UNEMP_10	ET_EMPSTATUS_10	EP_UNEMP_10	EPL_UNEMP_10	F_UNEMP_10	E_HBURD_OWN_10	ET_HOUSINGCOST_OWN_10	EP_HBURD_OWN_10	EPL_HBURD_OWN_10	F_HBURD_OWN_10	E_HBURD_RENT_10	ET_HOUSINGCOST_RENT_10	EP_HBURD_RENT_10	EPL_HBURD_RENT_10	F_HBURD_RENT_10	E_HBURD_10	ET_HOUSINGCOST_10	EP_HBURD_10	EPL_HBURD_10	F_HBURD_10	E_NOHSDP_10	ET_EDSTATUS_10	EP_NOHSDP_10	EPL_NOHSDP_10	F_NOHSDP_10	E_UNINSUR_12	ET_INSURSTATUS_12	EP_UNINSUR_12	EPL_UNINSUR_12	F_UNINSUR_12	E_AGE65_10	EP_AGE65_10	EPL_AGE65_10	F_AGE65_10	E_AGE17_10	EP_AGE17_10	EPL_AGE17_10	F_AGE17_10	E_DISABL_12	ET_DISABLSTATUS_12	EP_DISABL_12	EPL_DISABL_12	F_DISABL_12	E_SNGPNT_10	ET_FAMILIES_10	EP_SNGPNT_10	EPL_SNGPNT_10	F_SNGPNT_10	E_LIMENG_10	ET_POPAGE5UP_10	EP_LIMENG_10	EPL_LIMENG_10	F_LIMENG_10	E_MINRTY_10	ET_POPETHRACE_10	EP_MINRTY_10	EPL_MINRTY_10	F_MINRTY_10	E_STRHU_10	E_MUNIT_10	EP_MUNIT_10	EPL_MUNIT_10	F_MUNIT_10	E_MOBILE_10	EP_MOBILE_10	EPL_MOBILE_10	E_CROWD_10	ET_OCCUPANTS_10	EP_CROWD_10	EPL_CROWD_10	F_CROWD_10	E_NOVEH_10	ET_KNOWNVEH_10	EP_NOVEH_10	EPL_NOVEH_10	F_NOVEH_10	E_GROUPQ_10	ET_HHTYPE_10	EP_GROUPQ_10	EPL_GROUPQ_10	F_GROUPQ_10	SPL_THEME1_10	RPL_THEME1_10	F_THEME1_10	SPL_THEME2_10	RPL_THEME2_10	F_THEME2_10	SPL_THEME3_10	RPL_THEME3_10	F_THEME3_10	SPL_THEME4_10	RPL_THEME4_10	F_THEME4_10	SPL_THEMES_10	RPL_THEMES_10	F_TOTAL_10	E_TOTPOP_20	E_HU_20	E_HH_20	E_POV150_20	ET_POVSTATUS_20	EP_POV150_20	EPL_POV150_20	F_POV150_20	E_UNEMP_20	ET_EMPSTATUS_20	EP_UNEMP_20	EPL_UNEMP_20	F_UNEMP_20	E_HBURD_OWN_20	ET_HOUSINGCOST_OWN_20	EP_HBURD_OWN_20	EPL_HBURD_OWN_20	F_HBURD_OWN_20	E_HBURD_RENT_20	ET_HOUSINGCOST_RENT_20	EP_HBURD_RENT_20	EPL_HBURD_RENT_20	F_HBURD_RENT_20	E_HBURD_20	ET_HOUSINGCOST_20	EP_HBURD_20	EPL_HBURD_20	F_HBURD_20	E_NOHSDP_20	ET_EDSTATUS_20	EP_NOHSDP_20	EPL_NOHSDP_20	F_NOHSDP_20	E_UNINSUR_20	ET_INSURSTATUS_20	EP_UNINSUR_20	EPL_UNINSUR_20	F_UNINSUR_20	E_AGE65_20	EP_AGE65_20	EPL_AGE65_20	E_AGE17_20	EP_AGE17_20	EPL_AGE17_20	F_AGE17_20	E_DISABL_20	ET_DISABLSTATUS_20	EP_DISABL_20	EPL_DISABL_20	F_DISABL_20	E_SNGPNT_20	ET_FAMILIES_20	EP_SNGPNT_20	EPL_SNGPNT_20	F_SNGPNT_20	E_LIMENG_20	ET_POPAGE5UP_20	EP_LIMENG_20	EPL_LIMENG_20	F_LIMENG_20	E_MINRTY_20	ET_POPETHRACE_20	EP_MINRTY_20	EPL_MINRTY_20	F_MINRTY_20	E_STRHU_20	E_MUNIT_20	EP_MUNIT_20	EPL_MUNIT_20	F_MUNIT_20	E_MOBILE_20	EP_MOBILE_20	EPL_MOBILE_20	E_CROWD_20	ET_OCCUPANTS_20	EP_CROWD_20	EPL_CROWD_20	F_CROWD_20	E_NOVEH_20	ET_KNOWNVEH_20	EP_NOVEH_20	EPL_NOVEH_20	F_NOVEH_20	E_GROUPQ_20	ET_HHTYPE_20	EP_GROUPQ_20	EPL_GROUPQ_20	SPL_THEME1_20	RPL_THEME1_20	F_THEME1_20	SPL_THEME2_20	RPL_THEME2_20	F_THEME2_20	SPL_THEME3_20	RPL_THEME3_20	F_THEME3_20	SPL_THEME4_20	RPL_THEME4_20	F_THEME4_20	SPL_THEMES_20	RPL_THEMES_20	F_TOTAL_20
34001000100	34	001	000100	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2907	1088	983	1127	2907	38.76849	0.8482	1	144	1433	10.048849	0.7544	1	280	435	64.36782	0.9529	1	204	548	37.22628	0.2998	0	484	983	49.23703	0.7813	1	468	1759	26.60603	0.8634	1	532	2543	20.92017	0.8978	1	250	8.599931	0.1777	0	944	32.47334	0.94170	1	186	1851	10.04862	0.2706	0	266	678	39.233038	0.8981	1	177	2611	6.779012	0.7778	1	1928	2907	66.32267	0.7743	1	1088	113	10.386029	0.6229	0	9	0.8272059	0.7223	80	983	8.138352	0.8657	1	265	983	26.95829	0.7354	0	0	2907	0.000000	0.3512	0	4.1451	0.8935	5	3.06590	0.7944	3	0.7743	0.7667	1	3.2975	0.8414	1	11.28280	0.8862	10	2157	941	784	1182	2157	54.79833	0.9571	1	242	1058	22.873346	0.9922	1	215	342	62.86550	0.9780	1	316	442	71.49321	0.9481	1	531	784	67.72959	0.9893	1	396	1274	31.08320	0.9497	1	266	2157	12.331943	0.9041	1	185	8.576727	0.09430	552	25.59110	0.8128	1	297	1605	18.504673	0.74880	0	83	510	16.27451	0.6090	0	251	2020	12.425743	0.8710	1	1852	2157	85.85999	0.8476	1	941	118	12.5398512	0.6385	0	0	0.0000000	0.3216	67	784	8.545918	0.8657	1	212	784	27.04082	0.7502	1	0	2157	0.0000000	0.1517	4.7924	0.9850	5	3.13590	0.8217	2	0.8476	0.8400	1	2.7277	0.6085	2	11.50360	0.9104	10
34001000200	34	001	000200	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3189	2217	1473	519	3189	16.27469	0.4806	0	109	1558	6.996149	0.5179	0	573	955	60.00000	0.9323	1	199	518	38.41699	0.3261	0	772	1473	52.41005	0.8418	1	405	2579	15.70376	0.6491	0	484	3547	13.64533	0.7154	0	847	26.560050	0.9629	1	436	13.67200	0.08181	0	608	3005	20.23295	0.8466	1	42	857	4.900817	0.1204	0	422	3072	13.736979	0.8799	1	1792	3189	56.19316	0.7390	0	2217	901	40.640505	0.8693	1	0	0.0000000	0.3251	48	1473	3.258656	0.7064	0	250	1473	16.97217	0.6444	0	0	3189	0.000000	0.3512	0	3.2048	0.6963	1	2.89161	0.7231	3	0.7390	0.7317	0	2.8964	0.6887	1	9.73181	0.7340	5	3510	2046	1353	1021	3510	29.08832	0.7682	1	121	1852	6.533477	0.6717	0	343	696	49.28161	0.9273	1	416	657	63.31811	0.8696	1	759	1353	56.09756	0.9321	1	553	2338	23.65269	0.8871	1	354	3510	10.085470	0.8530	1	643	18.319088	0.60310	1002	28.54701	0.9055	1	450	2508	17.942584	0.72330	0	237	786	30.15267	0.8539	1	534	3375	15.822222	0.9062	1	2534	3510	72.19373	0.7818	1	2046	906	44.2815249	0.8690	1	0	0.0000000	0.3216	119	1353	8.795270	0.8711	1	324	1353	23.94678	0.7255	0	0	3510	0.0000000	0.1517	4.1121	0.9003	4	3.99200	0.9781	3	0.7818	0.7747	1	2.9389	0.7011	2	11.82480	0.9310	10
34001000300	34	001	000300	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3997	1823	1357	1401	3968	35.30746	0.8164	1	382	2238	17.068811	0.9376	1	176	329	53.49544	0.8855	1	604	1028	58.75486	0.7947	1	780	1357	57.47973	0.9165	1	920	2677	34.36683	0.9346	1	1351	4149	32.56206	0.9811	1	314	7.855892	0.1437	0	937	23.44258	0.55900	0	319	3054	10.44532	0.3000	0	187	782	23.913044	0.7498	0	1080	3671	29.419777	0.9742	1	3357	3997	83.98799	0.8419	1	1823	363	19.912233	0.7535	1	0	0.0000000	0.3251	150	1357	11.053795	0.9136	1	651	1357	47.97347	0.8585	1	0	3997	0.000000	0.3512	0	4.5862	0.9691	5	2.72670	0.6360	1	0.8419	0.8336	1	3.2019	0.8054	3	11.35670	0.8920	10	3801	1640	1226	1857	3801	48.85556	0.9333	1	226	1800	12.555556	0.9267	1	111	280	39.64286	0.8339	1	608	946	64.27061	0.8842	1	719	1226	58.64600	0.9528	1	650	2275	28.57143	0.9337	1	1027	3801	27.019206	0.9914	1	380	9.997369	0.14040	1223	32.17574	0.9607	1	219	2578	8.494957	0.15680	0	268	909	29.48295	0.8456	1	940	3400	27.647059	0.9728	1	3318	3801	87.29282	0.8579	1	1640	262	15.9756098	0.6917	0	0	0.0000000	0.3216	124	1226	10.114192	0.8955	1	477	1226	38.90701	0.8258	1	0	3801	0.0000000	0.1517	4.7379	0.9829	5	3.07630	0.8013	3	0.8579	0.8501	1	2.8863	0.6781	2	11.55840	0.9150	11
34001000400	34	001	000400	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2902	2683	1401	1172	2902	40.38594	0.8615	1	190	1389	13.678906	0.8811	1	364	707	51.48515	0.8627	1	507	694	73.05476	0.9503	1	871	1401	62.16988	0.9572	1	481	1981	24.28067	0.8339	1	674	3204	21.03620	0.8998	1	434	14.955203	0.6083	0	596	20.53756	0.33980	0	426	2607	16.34062	0.6886	0	111	652	17.024540	0.6204	0	215	2736	7.858187	0.8008	1	1792	2902	61.75052	0.7584	1	2683	2049	76.369735	0.9401	1	0	0.0000000	0.3251	69	1401	4.925053	0.7847	1	511	1401	36.47395	0.7992	1	72	2902	2.481048	0.8114	1	4.4335	0.9468	5	3.05790	0.7908	1	0.7584	0.7510	1	3.6605	0.9391	4	11.91030	0.9339	11	3178	2264	1390	1508	3176	47.48111	0.9246	1	172	1804	9.534368	0.8460	1	205	468	43.80342	0.8858	1	622	922	67.46204	0.9192	1	827	1390	59.49640	0.9587	1	364	2076	17.53372	0.8013	1	476	3178	14.977974	0.9390	1	483	15.198238	0.41220	539	16.96035	0.2484	0	319	2639	12.087912	0.38790	0	101	565	17.87611	0.6539	0	583	3022	19.291860	0.9349	1	2186	3178	68.78540	0.7658	1	2264	1609	71.0689046	0.9266	1	15	0.6625442	0.7078	226	1390	16.258993	0.9567	1	599	1390	43.09353	0.8474	1	20	3178	0.6293266	0.6292	4.4696	0.9558	5	2.63730	0.5864	1	0.7658	0.7588	1	4.0677	0.9762	3	11.94040	0.9387	10
34001000500	34	001	000500	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3483	1241	1027	1938	3483	55.64169	0.9533	1	124	1630	7.607362	0.5830	0	227	446	50.89686	0.8549	1	478	581	82.27194	0.9799	1	705	1027	68.64654	0.9863	1	733	2077	35.29129	0.9396	1	727	3258	22.31430	0.9149	1	377	10.824002	0.3081	0	1055	30.28998	0.90140	1	268	2401	11.16202	0.3549	0	209	763	27.391874	0.7940	1	911	3077	29.606760	0.9746	1	3036	3483	87.16624	0.8550	1	1241	52	4.190169	0.4505	0	4	0.3223207	0.6567	113	1027	11.002921	0.9128	1	422	1027	41.09056	0.8250	1	0	3483	0.000000	0.3512	0	4.3771	0.9379	4	3.33300	0.8766	3	0.8550	0.8467	1	3.1962	0.8026	2	11.76130	0.9229	10	3385	1185	945	1682	3364	50.00000	0.9391	1	72	1577	4.565631	0.4586	0	185	468	39.52991	0.8332	1	362	477	75.89099	0.9703	1	547	945	57.88360	0.9477	1	592	1983	29.85376	0.9422	1	738	3385	21.802068	0.9817	1	240	7.090103	0.05988	1129	33.35303	0.9689	1	135	2256	5.984043	0.04817	0	110	717	15.34170	0.5822	0	721	3076	23.439532	0.9569	1	3029	3385	89.48301	0.8727	1	1185	9	0.7594937	0.2382	0	0	0.0000000	0.3216	103	945	10.899471	0.9072	1	263	945	27.83069	0.7560	1	0	3385	0.0000000	0.1517	4.2693	0.9283	4	2.61605	0.5709	2	0.8727	0.8648	1	2.3747	0.4357	2	10.13275	0.7921	9
34001001100	34	001	001100	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2204	1204	1204	1185	2204	53.76588	0.9457	1	219	927	23.624596	0.9830	1	97	172	56.39535	0.9094	1	462	1032	44.76744	0.4746	0	559	1204	46.42857	0.7197	0	346	1440	24.02778	0.8306	1	469	1942	24.15036	0.9360	1	363	16.470054	0.7020	0	578	26.22505	0.74410	0	442	1558	28.36970	0.9675	1	247	396	62.373737	0.9898	1	104	2051	5.070697	0.7260	0	2118	2204	96.09800	0.9204	1	1204	570	47.342193	0.8858	1	0	0.0000000	0.3251	14	1204	1.162791	0.4877	0	817	1204	67.85714	0.9413	1	0	2204	0.000000	0.3512	0	4.4150	0.9451	4	4.12940	0.9805	2	0.9204	0.9114	1	2.9911	0.7243	2	12.45590	0.9597	9	1950	1267	1096	1131	1950	58.00000	0.9678	1	66	706	9.348442	0.8395	1	42	101	41.58416	0.8612	1	309	995	31.05528	0.1959	0	351	1096	32.02555	0.4782	0	510	1379	36.98332	0.9763	1	155	1950	7.948718	0.7660	1	392	20.102564	0.69880	447	22.92308	0.6712	0	570	1503	37.924152	0.99200	1	143	374	38.23529	0.9167	1	109	1841	5.920695	0.7464	0	1909	1950	97.89744	0.9529	1	1267	479	37.8058406	0.8464	1	0	0.0000000	0.3216	33	1096	3.010949	0.6446	0	743	1096	67.79197	0.9414	1	0	1950	0.0000000	0.1517	4.0278	0.8848	4	4.02510	0.9798	2	0.9529	0.9442	1	2.9057	0.6869	2	11.91150	0.9365	9

Code

# National data
svi_national %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID_2010_trt	FIPS_st	FIPS_county	FIPS_tract	state	state_name	county	region_number	region	division_number	division	E_TOTPOP_10	E_HU_10	E_HH_10	E_POV150_10	ET_POVSTATUS_10	EP_POV150_10	EPL_POV150_10	E_UNEMP_10	ET_EMPSTATUS_10	EP_UNEMP_10	EPL_UNEMP_10	E_HBURD_OWN_10	ET_HOUSINGCOST_OWN_10	EP_HBURD_OWN_10	EPL_HBURD_OWN_10	E_HBURD_RENT_10	ET_HOUSINGCOST_RENT_10	EP_HBURD_RENT_10	EPL_HBURD_RENT_10	E_HBURD_10	ET_HOUSINGCOST_10	EP_HBURD_10	EPL_HBURD_10	E_NOHSDP_10	ET_EDSTATUS_10	EP_NOHSDP_10	EPL_NOHSDP_10	F_NOHSDP_10	E_UNINSUR_12	ET_INSURSTATUS_12	EP_UNINSUR_12	EPL_UNINSUR_12	E_AGE65_10	EP_AGE65_10	EPL_AGE65_10	F_AGE65_10	E_AGE17_10	EP_AGE17_10	EPL_AGE17_10	F_AGE17_10	E_DISABL_12	ET_DISABLSTATUS_12	EP_DISABL_12	EPL_DISABL_12	F_DISABL_12	E_SNGPNT_10	ET_FAMILIES_10	EP_SNGPNT_10	EPL_SNGPNT_10	F_SNGPNT_10	E_LIMENG_10	ET_POPAGE5UP_10	EP_LIMENG_10	EPL_LIMENG_10	E_MINRTY_10	ET_POPETHRACE_10	EP_MINRTY_10	EPL_MINRTY_10	F_MINRTY_10	E_STRHU_10	E_MUNIT_10	EP_MUNIT_10	EPL_MUNIT_10	E_MOBILE_10	EP_MOBILE_10	EPL_MOBILE_10	F_MOBILE_10	E_CROWD_10	ET_OCCUPANTS_10	EP_CROWD_10	EPL_CROWD_10	E_NOVEH_10	ET_KNOWNVEH_10	EP_NOVEH_10	EPL_NOVEH_10	F_NOVEH_10	ET_HHTYPE_10	EPL_GROUPQ_10	SPL_THEME1_10	RPL_THEME1_10	F_THEME1_10	SPL_THEME2_10	RPL_THEME2_10	F_THEME2_10	SPL_THEME3_10	RPL_THEME3_10	F_THEME3_10	SPL_THEME4_10	RPL_THEME4_10	F_THEME4_10	SPL_THEMES_10	RPL_THEMES_10	F_TOTAL_10	E_TOTPOP_20	E_HU_20	E_HH_20	E_POV150_20	ET_POVSTATUS_20	EP_POV150_20	EPL_POV150_20	F_POV150_20	E_UNEMP_20	ET_EMPSTATUS_20	EP_UNEMP_20	EPL_UNEMP_20	E_HBURD_OWN_20	ET_HOUSINGCOST_OWN_20	EP_HBURD_OWN_20	EPL_HBURD_OWN_20	F_HBURD_OWN_20	E_HBURD_RENT_20	ET_HOUSINGCOST_RENT_20	EP_HBURD_RENT_20	EPL_HBURD_RENT_20	F_HBURD_RENT_20	E_HBURD_20	ET_HOUSINGCOST_20	EP_HBURD_20	EPL_HBURD_20	E_NOHSDP_20	ET_EDSTATUS_20	EP_NOHSDP_20	EPL_NOHSDP_20	E_UNINSUR_20	ET_INSURSTATUS_20	EP_UNINSUR_20	EPL_UNINSUR_20	F_UNINSUR_20	E_AGE65_20	EP_AGE65_20	EPL_AGE65_20	F_AGE65_20	E_AGE17_20	EP_AGE17_20	EPL_AGE17_20	F_AGE17_20	E_DISABL_20	ET_DISABLSTATUS_20	EP_DISABL_20	EPL_DISABL_20	F_DISABL_20	E_SNGPNT_20	ET_FAMILIES_20	EP_SNGPNT_20	EPL_SNGPNT_20	F_SNGPNT_20	E_LIMENG_20	ET_POPAGE5UP_20	EP_LIMENG_20	EPL_LIMENG_20	E_MINRTY_20	ET_POPETHRACE_20	EP_MINRTY_20	EPL_MINRTY_20	F_MINRTY_20	E_STRHU_20	E_MUNIT_20	EP_MUNIT_20	EPL_MUNIT_20	E_MOBILE_20	EP_MOBILE_20	EPL_MOBILE_20	F_MOBILE_20	E_CROWD_20	ET_OCCUPANTS_20	EP_CROWD_20	EPL_CROWD_20	E_NOVEH_20	ET_KNOWNVEH_20	EP_NOVEH_20	EPL_NOVEH_20	E_GROUPQ_20	ET_HHTYPE_20	EP_GROUPQ_20	EPL_GROUPQ_20	F_GROUPQ_20	SPL_THEME1_20	RPL_THEME1_20	F_THEME1_20	SPL_THEME2_20	RPL_THEME2_20	F_THEME2_20	SPL_THEME3_20	RPL_THEME3_20	F_THEME3_20	SPL_THEME4_20	RPL_THEME4_20	F_THEME4_20	SPL_THEMES_20	RPL_THEMES_20	F_TOTAL_20
01001020100	01	001	020100	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	1809	771	696	297	1809	16.41791	0.3871	36	889	4.049494	0.1790	127	598	21.23746	0.20770	47	98	47.95918	0.5767	174	696	25.00000	0.18790	196	1242	15.780998	0.6093	0	186	1759	10.574190	0.3790	222	12.271973	0.4876	0	445	24.59923	0.5473	0	298	1335	22.32210	0.8454	1	27	545	4.954128	0.09275	0	36	1705	2.1114370	0.59040	385	1809	21.282477	0.4524	0	771	0	0.0000000	0.1224	92	11.9325551	0.8005	1	0	696	0.0000000	0.1238	50	696	7.183908	0.6134	0	1809	0.364	1.74230	0.28200	0	2.56345	0.5296	1	0.4524	0.4482	0	2.0241	0.2519	1	6.78225	0.3278	2	1941	710	693	352	1941	18.13498	0.4630	0	18	852	2.112676	0.15070	81	507	15.976331	0.26320	0	63	186	33.87097	0.2913	0	144	693	20.77922	0.2230	187	1309	14.285714	0.6928	187	1941	9.634209	0.6617	0	295	15.19835	0.4601	0	415	21.38073	0.4681	0	391	1526	25.62254	0.9011	1	58	555	10.45045	0.3451	0	0	1843	0.0000000	0.09479	437	1941	22.51417	0.3902	0	710	0	0.0000000	0.1079	88	12.3943662	0.8263	1	0	693	0.0000000	0.09796	10	693	1.443001	0.1643	0	1941	0.000000	0.1831	0	2.19120	0.4084	0	2.26919	0.3503	1	0.3902	0.3869	0	1.37956	0.07216	1	6.23015	0.2314	2
01001020200	01	001	020200	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	2020	816	730	495	1992	24.84940	0.5954	68	834	8.153477	0.5754	49	439	11.16173	0.02067	105	291	36.08247	0.3019	154	730	21.09589	0.09312	339	1265	26.798419	0.8392	1	313	2012	15.556660	0.6000	204	10.099010	0.3419	0	597	29.55446	0.8192	1	359	1515	23.69637	0.8791	1	132	456	28.947368	0.83510	1	15	1890	0.7936508	0.40130	1243	2020	61.534653	0.7781	1	816	0	0.0000000	0.1224	34	4.1666667	0.6664	0	13	730	1.7808219	0.5406	115	730	15.753425	0.8382	1	2020	0.364	2.70312	0.56650	1	3.27660	0.8614	3	0.7781	0.7709	1	2.5316	0.5047	1	9.28942	0.6832	6	1757	720	573	384	1511	25.41363	0.6427	0	29	717	4.044630	0.41320	33	392	8.418367	0.03542	0	116	181	64.08840	0.9086	1	149	573	26.00349	0.4041	139	1313	10.586443	0.5601	91	1533	5.936073	0.4343	0	284	16.16392	0.5169	0	325	18.49744	0.2851	0	164	1208	13.57616	0.4127	0	42	359	11.69916	0.3998	0	0	1651	0.0000000	0.09479	1116	1757	63.51736	0.7591	1	720	3	0.4166667	0.2470	5	0.6944444	0.5106	0	9	573	1.5706806	0.46880	57	573	9.947644	0.7317	212	1757	12.066022	0.9549	1	2.45440	0.4888	0	1.70929	0.1025	0	0.7591	0.7527	1	2.91300	0.68620	1	7.83579	0.4802	2
01001020300	01	001	020300	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	3543	1403	1287	656	3533	18.56779	0.4443	93	1552	5.992268	0.3724	273	957	28.52665	0.45780	178	330	53.93939	0.7152	451	1287	35.04274	0.49930	346	2260	15.309734	0.5950	0	252	3102	8.123791	0.2596	487	13.745413	0.5868	0	998	28.16822	0.7606	1	371	2224	16.68165	0.6266	0	126	913	13.800657	0.46350	0	0	3365	0.0000000	0.09298	637	3543	17.979114	0.4049	0	1403	10	0.7127584	0.3015	2	0.1425517	0.4407	0	0	1287	0.0000000	0.1238	101	1287	7.847708	0.6443	0	3543	0.364	2.17060	0.41010	0	2.53048	0.5116	1	0.4049	0.4011	0	1.8743	0.1942	0	6.98028	0.3576	1	3694	1464	1351	842	3694	22.79372	0.5833	0	53	1994	2.657974	0.22050	117	967	12.099276	0.11370	0	147	384	38.28125	0.3856	0	264	1351	19.54108	0.1827	317	2477	12.797739	0.6460	127	3673	3.457664	0.2308	0	464	12.56091	0.3088	0	929	25.14889	0.7080	0	473	2744	17.23761	0.6211	0	263	975	26.97436	0.8234	1	128	3586	3.5694367	0.70770	1331	3694	36.03140	0.5515	0	1464	26	1.7759563	0.3675	14	0.9562842	0.5389	0	35	1351	2.5906736	0.60550	42	1351	3.108808	0.3415	0	3694	0.000000	0.1831	0	1.86330	0.3063	0	3.16900	0.8380	1	0.5515	0.5468	0	2.03650	0.26830	0	7.62030	0.4460	1
01001020400	01	001	020400	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	4840	1957	1839	501	4840	10.35124	0.2177	101	2129	4.744011	0.2447	310	1549	20.01291	0.17080	89	290	30.68966	0.2044	399	1839	21.69657	0.10540	274	3280	8.353658	0.3205	0	399	4293	9.294200	0.3171	955	19.731405	0.8643	1	1195	24.69008	0.5530	0	625	3328	18.78005	0.7233	0	152	1374	11.062591	0.34710	0	10	4537	0.2204100	0.22560	297	4840	6.136364	0.1647	0	1957	33	1.6862545	0.3843	25	1.2774655	0.5516	0	14	1839	0.7612833	0.3564	19	1839	1.033170	0.1127	0	4840	0.364	1.20540	0.13470	0	2.71330	0.6129	1	0.1647	0.1632	0	1.7690	0.1591	0	5.85240	0.1954	1	3539	1741	1636	503	3539	14.21305	0.3472	0	39	1658	2.352232	0.17990	219	1290	16.976744	0.30880	0	74	346	21.38728	0.1037	0	293	1636	17.90954	0.1333	173	2775	6.234234	0.3351	169	3529	4.788892	0.3448	0	969	27.38062	0.9225	1	510	14.41085	0.1208	0	670	3019	22.19278	0.8194	1	148	1137	13.01671	0.4541	0	89	3409	2.6107363	0.64690	454	3539	12.82848	0.2364	0	1741	143	8.2136703	0.6028	0	0.0000000	0.2186	0	10	1636	0.6112469	0.28340	72	1636	4.400978	0.4538	0	3539	0.000000	0.1831	0	1.34030	0.1575	0	2.96370	0.7496	2	0.2364	0.2344	0	1.74170	0.16270	0	6.28210	0.2389	2
01001020500	01	001	020500	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	9938	3969	3741	1096	9938	11.02838	0.2364	188	4937	3.807981	0.1577	426	2406	17.70574	0.11050	528	1335	39.55056	0.3753	954	3741	25.50120	0.20140	293	5983	4.897209	0.1655	0	740	10110	7.319486	0.2211	837	8.422218	0.2408	0	3012	30.30791	0.8455	1	759	7155	10.60797	0.2668	0	476	2529	18.821669	0.63540	0	78	9297	0.8389803	0.41110	1970	9938	19.822902	0.4330	0	3969	306	7.7097506	0.6153	0	0.0000000	0.2198	0	7	3741	0.1871157	0.2535	223	3741	5.960973	0.5483	0	9938	0.364	0.98210	0.08468	0	2.39960	0.4381	1	0.4330	0.4290	0	2.0009	0.2430	0	5.81560	0.1905	1	10674	4504	4424	1626	10509	15.47245	0.3851	0	81	5048	1.604596	0.09431	321	2299	13.962592	0.17970	0	711	2125	33.45882	0.2836	0	1032	4424	23.32731	0.3109	531	6816	7.790493	0.4251	301	10046	2.996217	0.1894	0	1613	15.11149	0.4553	0	2765	25.90407	0.7494	0	1124	7281	15.43744	0.5253	0	342	2912	11.74451	0.4019	0	52	9920	0.5241935	0.35230	2603	10674	24.38636	0.4160	0	4504	703	15.6083481	0.7378	29	0.6438721	0.5037	0	37	4424	0.8363472	0.33420	207	4424	4.679023	0.4754	176	10674	1.648866	0.7598	1	1.40481	0.1743	0	2.48420	0.4802	0	0.4160	0.4125	0	2.81090	0.63730	1	7.11591	0.3654	1
01001020600	01	001	020600	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	3402	1456	1308	735	3402	21.60494	0.5199	134	1720	7.790698	0.5436	242	1032	23.44961	0.28010	62	276	22.46377	0.1035	304	1308	23.24159	0.14070	301	2151	13.993491	0.5510	0	355	3445	10.304790	0.3656	386	11.346267	0.4232	0	931	27.36626	0.7200	0	440	2439	18.04018	0.6912	0	143	924	15.476190	0.52900	0	4	3254	0.1229256	0.19840	723	3402	21.252205	0.4519	0	1456	18	1.2362637	0.3507	433	29.7390110	0.9468	1	16	1308	1.2232416	0.4493	28	1308	2.140673	0.2298	0	3402	0.364	2.12080	0.39510	0	2.56180	0.5288	0	0.4519	0.4477	0	2.3406	0.4048	1	7.47510	0.4314	1	3536	1464	1330	1279	3523	36.30429	0.8215	1	34	1223	2.780049	0.23780	321	1111	28.892889	0.75870	1	67	219	30.59361	0.2305	0	388	1330	29.17293	0.5075	306	2380	12.857143	0.6480	415	3496	11.870709	0.7535	1	547	15.46946	0.4760	0	982	27.77149	0.8327	1	729	2514	28.99761	0.9488	1	95	880	10.79545	0.3601	0	0	3394	0.0000000	0.09479	985	3536	27.85633	0.4608	0	1464	0	0.0000000	0.1079	364	24.8633880	0.9300	1	0	1330	0.0000000	0.09796	17	1330	1.278196	0.1463	0	3536	0.000000	0.1831	0	2.96830	0.6434	2	2.71239	0.6156	2	0.4608	0.4569	0	1.46526	0.08976	1	7.60675	0.4440	5

Next, let’s filter our dataset only to NMTC eligible tracts:

Code

# Divisional data
svi_divisional_nmtc_eligible <- left_join(svi_divisional, nmtc_eligible_df, join_by("GEOID_2010_trt" == "GEOID10")) %>% filter(tolower(nmtc_eligibility) == "yes")

svi_divisional_nmtc_eligible %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID_2010_trt	FIPS_st	FIPS_county	FIPS_tract	state	state_name	county	region_number	region	division_number	division	E_TOTPOP_10	E_HU_10	E_HH_10	E_POV150_10	ET_POVSTATUS_10	EP_POV150_10	EPL_POV150_10	F_POV150_10	E_UNEMP_10	ET_EMPSTATUS_10	EP_UNEMP_10	EPL_UNEMP_10	F_UNEMP_10	E_HBURD_OWN_10	ET_HOUSINGCOST_OWN_10	EP_HBURD_OWN_10	EPL_HBURD_OWN_10	F_HBURD_OWN_10	E_HBURD_RENT_10	ET_HOUSINGCOST_RENT_10	EP_HBURD_RENT_10	EPL_HBURD_RENT_10	F_HBURD_RENT_10	E_HBURD_10	ET_HOUSINGCOST_10	EP_HBURD_10	EPL_HBURD_10	F_HBURD_10	E_NOHSDP_10	ET_EDSTATUS_10	EP_NOHSDP_10	EPL_NOHSDP_10	F_NOHSDP_10	E_UNINSUR_12	ET_INSURSTATUS_12	EP_UNINSUR_12	EPL_UNINSUR_12	F_UNINSUR_12	E_AGE65_10	EP_AGE65_10	EPL_AGE65_10	F_AGE65_10	E_AGE17_10	EP_AGE17_10	EPL_AGE17_10	F_AGE17_10	E_DISABL_12	ET_DISABLSTATUS_12	EP_DISABL_12	EPL_DISABL_12	F_DISABL_12	E_SNGPNT_10	ET_FAMILIES_10	EP_SNGPNT_10	EPL_SNGPNT_10	F_SNGPNT_10	E_LIMENG_10	ET_POPAGE5UP_10	EP_LIMENG_10	EPL_LIMENG_10	F_LIMENG_10	E_MINRTY_10	ET_POPETHRACE_10	EP_MINRTY_10	EPL_MINRTY_10	F_MINRTY_10	E_STRHU_10	E_MUNIT_10	EP_MUNIT_10	EPL_MUNIT_10	F_MUNIT_10	E_MOBILE_10	EP_MOBILE_10	EPL_MOBILE_10	E_CROWD_10	ET_OCCUPANTS_10	EP_CROWD_10	EPL_CROWD_10	F_CROWD_10	E_NOVEH_10	ET_KNOWNVEH_10	EP_NOVEH_10	EPL_NOVEH_10	F_NOVEH_10	E_GROUPQ_10	ET_HHTYPE_10	EP_GROUPQ_10	EPL_GROUPQ_10	F_GROUPQ_10	SPL_THEME1_10	RPL_THEME1_10	F_THEME1_10	SPL_THEME2_10	RPL_THEME2_10	F_THEME2_10	SPL_THEME3_10	RPL_THEME3_10	F_THEME3_10	SPL_THEME4_10	RPL_THEME4_10	F_THEME4_10	SPL_THEMES_10	RPL_THEMES_10	F_TOTAL_10	E_TOTPOP_20	E_HU_20	E_HH_20	E_POV150_20	ET_POVSTATUS_20	EP_POV150_20	EPL_POV150_20	F_POV150_20	E_UNEMP_20	ET_EMPSTATUS_20	EP_UNEMP_20	EPL_UNEMP_20	F_UNEMP_20	E_HBURD_OWN_20	ET_HOUSINGCOST_OWN_20	EP_HBURD_OWN_20	EPL_HBURD_OWN_20	F_HBURD_OWN_20	E_HBURD_RENT_20	ET_HOUSINGCOST_RENT_20	EP_HBURD_RENT_20	EPL_HBURD_RENT_20	F_HBURD_RENT_20	E_HBURD_20	ET_HOUSINGCOST_20	EP_HBURD_20	EPL_HBURD_20	F_HBURD_20	E_NOHSDP_20	ET_EDSTATUS_20	EP_NOHSDP_20	EPL_NOHSDP_20	F_NOHSDP_20	E_UNINSUR_20	ET_INSURSTATUS_20	EP_UNINSUR_20	EPL_UNINSUR_20	F_UNINSUR_20	E_AGE65_20	EP_AGE65_20	EPL_AGE65_20	E_AGE17_20	EP_AGE17_20	EPL_AGE17_20	F_AGE17_20	E_DISABL_20	ET_DISABLSTATUS_20	EP_DISABL_20	EPL_DISABL_20	F_DISABL_20	E_SNGPNT_20	ET_FAMILIES_20	EP_SNGPNT_20	EPL_SNGPNT_20	F_SNGPNT_20	E_LIMENG_20	ET_POPAGE5UP_20	EP_LIMENG_20	EPL_LIMENG_20	F_LIMENG_20	E_MINRTY_20	ET_POPETHRACE_20	EP_MINRTY_20	EPL_MINRTY_20	F_MINRTY_20	E_STRHU_20	E_MUNIT_20	EP_MUNIT_20	EPL_MUNIT_20	F_MUNIT_20	E_MOBILE_20	EP_MOBILE_20	EPL_MOBILE_20	E_CROWD_20	ET_OCCUPANTS_20	EP_CROWD_20	EPL_CROWD_20	F_CROWD_20	E_NOVEH_20	ET_KNOWNVEH_20	EP_NOVEH_20	EPL_NOVEH_20	F_NOVEH_20	E_GROUPQ_20	ET_HHTYPE_20	EP_GROUPQ_20	EPL_GROUPQ_20	SPL_THEME1_20	RPL_THEME1_20	F_THEME1_20	SPL_THEME2_20	RPL_THEME2_20	F_THEME2_20	SPL_THEME3_20	RPL_THEME3_20	F_THEME3_20	SPL_THEME4_20	RPL_THEME4_20	F_THEME4_20	SPL_THEMES_20	RPL_THEMES_20	F_TOTAL_20	nmtc_eligibility
34001000100	34	001	000100	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2907	1088	983	1127	2907	38.76849	0.8482	1	144	1433	10.048849	0.7544	1	280	435	64.36782	0.9529	1	204	548	37.22628	0.2998	0	484	983	49.23703	0.7813	1	468	1759	26.60603	0.8634	1	532	2543	20.92017	0.8978	1	250	8.599931	0.1777	0	944	32.47334	0.94170	1	186	1851	10.04862	0.2706	0	266	678	39.233038	0.8981	1	177	2611	6.779012	0.7778	1	1928	2907	66.32267	0.7743	1	1088	113	10.386029	0.6229	0	9	0.8272059	0.7223	80	983	8.138352	0.8657	1	265	983	26.95829	0.7354	0	0	2907	0.000000	0.3512	0	4.1451	0.8935	5	3.06590	0.7944	3	0.7743	0.7667	1	3.2975	0.8414	1	11.28280	0.8862	10	2157	941	784	1182	2157	54.79833	0.9571	1	242	1058	22.873346	0.9922	1	215	342	62.86550	0.9780	1	316	442	71.49321	0.9481	1	531	784	67.72959	0.9893	1	396	1274	31.08320	0.9497	1	266	2157	12.331943	0.9041	1	185	8.576727	0.09430	552	25.59110	0.8128	1	297	1605	18.504673	0.74880	0	83	510	16.27451	0.6090	0	251	2020	12.425743	0.8710	1	1852	2157	85.85999	0.8476	1	941	118	12.5398512	0.6385	0	0	0.0000000	0.3216	67	784	8.545918	0.8657	1	212	784	27.04082	0.7502	1	0	2157	0.0000000	0.1517	4.7924	0.9850	5	3.13590	0.8217	2	0.8476	0.8400	1	2.7277	0.6085	2	11.50360	0.9104	10	Yes
34001000200	34	001	000200	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3189	2217	1473	519	3189	16.27469	0.4806	0	109	1558	6.996149	0.5179	0	573	955	60.00000	0.9323	1	199	518	38.41699	0.3261	0	772	1473	52.41005	0.8418	1	405	2579	15.70376	0.6491	0	484	3547	13.64533	0.7154	0	847	26.560050	0.9629	1	436	13.67200	0.08181	0	608	3005	20.23295	0.8466	1	42	857	4.900817	0.1204	0	422	3072	13.736979	0.8799	1	1792	3189	56.19316	0.7390	0	2217	901	40.640505	0.8693	1	0	0.0000000	0.3251	48	1473	3.258656	0.7064	0	250	1473	16.97217	0.6444	0	0	3189	0.000000	0.3512	0	3.2048	0.6963	1	2.89161	0.7231	3	0.7390	0.7317	0	2.8964	0.6887	1	9.73181	0.7340	5	3510	2046	1353	1021	3510	29.08832	0.7682	1	121	1852	6.533477	0.6717	0	343	696	49.28161	0.9273	1	416	657	63.31811	0.8696	1	759	1353	56.09756	0.9321	1	553	2338	23.65269	0.8871	1	354	3510	10.085470	0.8530	1	643	18.319088	0.60310	1002	28.54701	0.9055	1	450	2508	17.942584	0.72330	0	237	786	30.15267	0.8539	1	534	3375	15.822222	0.9062	1	2534	3510	72.19373	0.7818	1	2046	906	44.2815249	0.8690	1	0	0.0000000	0.3216	119	1353	8.795270	0.8711	1	324	1353	23.94678	0.7255	0	0	3510	0.0000000	0.1517	4.1121	0.9003	4	3.99200	0.9781	3	0.7818	0.7747	1	2.9389	0.7011	2	11.82480	0.9310	10	Yes
34001000300	34	001	000300	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3997	1823	1357	1401	3968	35.30746	0.8164	1	382	2238	17.068811	0.9376	1	176	329	53.49544	0.8855	1	604	1028	58.75486	0.7947	1	780	1357	57.47973	0.9165	1	920	2677	34.36683	0.9346	1	1351	4149	32.56206	0.9811	1	314	7.855892	0.1437	0	937	23.44258	0.55900	0	319	3054	10.44532	0.3000	0	187	782	23.913044	0.7498	0	1080	3671	29.419777	0.9742	1	3357	3997	83.98799	0.8419	1	1823	363	19.912233	0.7535	1	0	0.0000000	0.3251	150	1357	11.053795	0.9136	1	651	1357	47.97347	0.8585	1	0	3997	0.000000	0.3512	0	4.5862	0.9691	5	2.72670	0.6360	1	0.8419	0.8336	1	3.2019	0.8054	3	11.35670	0.8920	10	3801	1640	1226	1857	3801	48.85556	0.9333	1	226	1800	12.555556	0.9267	1	111	280	39.64286	0.8339	1	608	946	64.27061	0.8842	1	719	1226	58.64600	0.9528	1	650	2275	28.57143	0.9337	1	1027	3801	27.019206	0.9914	1	380	9.997369	0.14040	1223	32.17574	0.9607	1	219	2578	8.494957	0.15680	0	268	909	29.48295	0.8456	1	940	3400	27.647059	0.9728	1	3318	3801	87.29282	0.8579	1	1640	262	15.9756098	0.6917	0	0	0.0000000	0.3216	124	1226	10.114192	0.8955	1	477	1226	38.90701	0.8258	1	0	3801	0.0000000	0.1517	4.7379	0.9829	5	3.07630	0.8013	3	0.8579	0.8501	1	2.8863	0.6781	2	11.55840	0.9150	11	Yes
34001000400	34	001	000400	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2902	2683	1401	1172	2902	40.38594	0.8615	1	190	1389	13.678906	0.8811	1	364	707	51.48515	0.8627	1	507	694	73.05476	0.9503	1	871	1401	62.16988	0.9572	1	481	1981	24.28067	0.8339	1	674	3204	21.03620	0.8998	1	434	14.955203	0.6083	0	596	20.53756	0.33980	0	426	2607	16.34062	0.6886	0	111	652	17.024540	0.6204	0	215	2736	7.858187	0.8008	1	1792	2902	61.75052	0.7584	1	2683	2049	76.369735	0.9401	1	0	0.0000000	0.3251	69	1401	4.925053	0.7847	1	511	1401	36.47395	0.7992	1	72	2902	2.481048	0.8114	1	4.4335	0.9468	5	3.05790	0.7908	1	0.7584	0.7510	1	3.6605	0.9391	4	11.91030	0.9339	11	3178	2264	1390	1508	3176	47.48111	0.9246	1	172	1804	9.534368	0.8460	1	205	468	43.80342	0.8858	1	622	922	67.46204	0.9192	1	827	1390	59.49640	0.9587	1	364	2076	17.53372	0.8013	1	476	3178	14.977974	0.9390	1	483	15.198238	0.41220	539	16.96035	0.2484	0	319	2639	12.087912	0.38790	0	101	565	17.87611	0.6539	0	583	3022	19.291860	0.9349	1	2186	3178	68.78540	0.7658	1	2264	1609	71.0689046	0.9266	1	15	0.6625442	0.7078	226	1390	16.258993	0.9567	1	599	1390	43.09353	0.8474	1	20	3178	0.6293266	0.6292	4.4696	0.9558	5	2.63730	0.5864	1	0.7658	0.7588	1	4.0677	0.9762	3	11.94040	0.9387	10	Yes
34001000500	34	001	000500	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3483	1241	1027	1938	3483	55.64169	0.9533	1	124	1630	7.607362	0.5830	0	227	446	50.89686	0.8549	1	478	581	82.27194	0.9799	1	705	1027	68.64654	0.9863	1	733	2077	35.29129	0.9396	1	727	3258	22.31430	0.9149	1	377	10.824002	0.3081	0	1055	30.28998	0.90140	1	268	2401	11.16202	0.3549	0	209	763	27.391874	0.7940	1	911	3077	29.606760	0.9746	1	3036	3483	87.16624	0.8550	1	1241	52	4.190169	0.4505	0	4	0.3223207	0.6567	113	1027	11.002921	0.9128	1	422	1027	41.09056	0.8250	1	0	3483	0.000000	0.3512	0	4.3771	0.9379	4	3.33300	0.8766	3	0.8550	0.8467	1	3.1962	0.8026	2	11.76130	0.9229	10	3385	1185	945	1682	3364	50.00000	0.9391	1	72	1577	4.565631	0.4586	0	185	468	39.52991	0.8332	1	362	477	75.89099	0.9703	1	547	945	57.88360	0.9477	1	592	1983	29.85376	0.9422	1	738	3385	21.802068	0.9817	1	240	7.090103	0.05988	1129	33.35303	0.9689	1	135	2256	5.984043	0.04817	0	110	717	15.34170	0.5822	0	721	3076	23.439532	0.9569	1	3029	3385	89.48301	0.8727	1	1185	9	0.7594937	0.2382	0	0	0.0000000	0.3216	103	945	10.899471	0.9072	1	263	945	27.83069	0.7560	1	0	3385	0.0000000	0.1517	4.2693	0.9283	4	2.61605	0.5709	2	0.8727	0.8648	1	2.3747	0.4357	2	10.13275	0.7921	9	Yes
34001001100	34	001	001100	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2204	1204	1204	1185	2204	53.76588	0.9457	1	219	927	23.624596	0.9830	1	97	172	56.39535	0.9094	1	462	1032	44.76744	0.4746	0	559	1204	46.42857	0.7197	0	346	1440	24.02778	0.8306	1	469	1942	24.15036	0.9360	1	363	16.470054	0.7020	0	578	26.22505	0.74410	0	442	1558	28.36970	0.9675	1	247	396	62.373737	0.9898	1	104	2051	5.070697	0.7260	0	2118	2204	96.09800	0.9204	1	1204	570	47.342193	0.8858	1	0	0.0000000	0.3251	14	1204	1.162791	0.4877	0	817	1204	67.85714	0.9413	1	0	2204	0.000000	0.3512	0	4.4150	0.9451	4	4.12940	0.9805	2	0.9204	0.9114	1	2.9911	0.7243	2	12.45590	0.9597	9	1950	1267	1096	1131	1950	58.00000	0.9678	1	66	706	9.348442	0.8395	1	42	101	41.58416	0.8612	1	309	995	31.05528	0.1959	0	351	1096	32.02555	0.4782	0	510	1379	36.98332	0.9763	1	155	1950	7.948718	0.7660	1	392	20.102564	0.69880	447	22.92308	0.6712	0	570	1503	37.924152	0.99200	1	143	374	38.23529	0.9167	1	109	1841	5.920695	0.7464	0	1909	1950	97.89744	0.9529	1	1267	479	37.8058406	0.8464	1	0	0.0000000	0.3216	33	1096	3.010949	0.6446	0	743	1096	67.79197	0.9414	1	0	1950	0.0000000	0.1517	4.0278	0.8848	4	4.02510	0.9798	2	0.9529	0.9442	1	2.9057	0.6869	2	11.91150	0.9365	9	Yes

Code

# National data
svi_national_nmtc_eligible <- left_join(svi_national, nmtc_eligible_df, join_by("GEOID_2010_trt" == "GEOID10")) %>% filter(tolower(nmtc_eligibility) == "yes")

svi_national_nmtc_eligible %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID_2010_trt	FIPS_st	FIPS_county	FIPS_tract	state	state_name	county	region_number	region	division_number	division	E_TOTPOP_10	E_HU_10	E_HH_10	E_POV150_10	ET_POVSTATUS_10	EP_POV150_10	EPL_POV150_10	F_POV150_10	E_UNEMP_10	ET_EMPSTATUS_10	EP_UNEMP_10	EPL_UNEMP_10	F_UNEMP_10	E_HBURD_OWN_10	ET_HOUSINGCOST_OWN_10	EP_HBURD_OWN_10	EPL_HBURD_OWN_10	E_HBURD_RENT_10	ET_HOUSINGCOST_RENT_10	EP_HBURD_RENT_10	EPL_HBURD_RENT_10	E_HBURD_10	ET_HOUSINGCOST_10	EP_HBURD_10	EPL_HBURD_10	E_NOHSDP_10	ET_EDSTATUS_10	EP_NOHSDP_10	EPL_NOHSDP_10	F_NOHSDP_10	E_UNINSUR_12	ET_INSURSTATUS_12	EP_UNINSUR_12	EPL_UNINSUR_12	E_AGE65_10	EP_AGE65_10	EPL_AGE65_10	E_AGE17_10	EP_AGE17_10	EPL_AGE17_10	F_AGE17_10	E_DISABL_12	ET_DISABLSTATUS_12	EP_DISABL_12	EPL_DISABL_12	F_DISABL_12	E_SNGPNT_10	ET_FAMILIES_10	EP_SNGPNT_10	EPL_SNGPNT_10	F_SNGPNT_10	E_LIMENG_10	ET_POPAGE5UP_10	EP_LIMENG_10	EPL_LIMENG_10	E_MINRTY_10	ET_POPETHRACE_10	EP_MINRTY_10	EPL_MINRTY_10	F_MINRTY_10	E_STRHU_10	E_MUNIT_10	EP_MUNIT_10	EPL_MUNIT_10	E_MOBILE_10	EP_MOBILE_10	EPL_MOBILE_10	F_MOBILE_10	E_CROWD_10	ET_OCCUPANTS_10	EP_CROWD_10	EPL_CROWD_10	F_CROWD_10	E_NOVEH_10	ET_KNOWNVEH_10	EP_NOVEH_10	EPL_NOVEH_10	F_NOVEH_10	E_GROUPQ_10	ET_HHTYPE_10	EP_GROUPQ_10	EPL_GROUPQ_10	F_GROUPQ_10	SPL_THEME1_10	RPL_THEME1_10	F_THEME1_10	SPL_THEME2_10	RPL_THEME2_10	F_THEME2_10	SPL_THEME3_10	RPL_THEME3_10	F_THEME3_10	SPL_THEME4_10	RPL_THEME4_10	F_THEME4_10	SPL_THEMES_10	RPL_THEMES_10	F_TOTAL_10	E_TOTPOP_20	E_HU_20	E_HH_20	E_POV150_20	ET_POVSTATUS_20	EP_POV150_20	EPL_POV150_20	F_POV150_20	E_UNEMP_20	ET_EMPSTATUS_20	EP_UNEMP_20	EPL_UNEMP_20	F_UNEMP_20	E_HBURD_OWN_20	ET_HOUSINGCOST_OWN_20	EP_HBURD_OWN_20	EPL_HBURD_OWN_20	F_HBURD_OWN_20	E_HBURD_RENT_20	ET_HOUSINGCOST_RENT_20	EP_HBURD_RENT_20	EPL_HBURD_RENT_20	F_HBURD_RENT_20	E_HBURD_20	ET_HOUSINGCOST_20	EP_HBURD_20	EPL_HBURD_20	F_HBURD_20	E_NOHSDP_20	ET_EDSTATUS_20	EP_NOHSDP_20	EPL_NOHSDP_20	F_NOHSDP_20	E_UNINSUR_20	ET_INSURSTATUS_20	EP_UNINSUR_20	EPL_UNINSUR_20	F_UNINSUR_20	E_AGE65_20	EP_AGE65_20	EPL_AGE65_20	F_AGE65_20	E_AGE17_20	EP_AGE17_20	EPL_AGE17_20	F_AGE17_20	E_DISABL_20	ET_DISABLSTATUS_20	EP_DISABL_20	EPL_DISABL_20	F_DISABL_20	E_SNGPNT_20	ET_FAMILIES_20	EP_SNGPNT_20	EPL_SNGPNT_20	F_SNGPNT_20	E_LIMENG_20	ET_POPAGE5UP_20	EP_LIMENG_20	EPL_LIMENG_20	E_MINRTY_20	ET_POPETHRACE_20	EP_MINRTY_20	EPL_MINRTY_20	F_MINRTY_20	E_STRHU_20	E_MUNIT_20	EP_MUNIT_20	EPL_MUNIT_20	E_MOBILE_20	EP_MOBILE_20	EPL_MOBILE_20	F_MOBILE_20	E_CROWD_20	ET_OCCUPANTS_20	EP_CROWD_20	EPL_CROWD_20	F_CROWD_20	E_NOVEH_20	ET_KNOWNVEH_20	EP_NOVEH_20	EPL_NOVEH_20	E_GROUPQ_20	ET_HHTYPE_20	EP_GROUPQ_20	EPL_GROUPQ_20	F_GROUPQ_20	SPL_THEME1_20	RPL_THEME1_20	F_THEME1_20	SPL_THEME2_20	RPL_THEME2_20	F_THEME2_20	SPL_THEME3_20	RPL_THEME3_20	F_THEME3_20	SPL_THEME4_20	RPL_THEME4_20	F_THEME4_20	SPL_THEMES_20	RPL_THEMES_20	F_TOTAL_20	nmtc_eligibility
01001020200	01	001	020200	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	2020	816	730	495	1992	24.84940	0.5954	0	68	834	8.153477	0.57540	0	49	439	11.16173	0.02067	105	291	36.08247	0.30190	154	730	21.09589	0.09312	339	1265	26.79842	0.8392	1	313	2012	15.55666	0.6000	204	10.09901	0.3419	597	29.55446	0.8192	1	359	1515	23.69637	0.8791	1	132	456	28.947368	0.8351	1	15	1890	0.7936508	0.40130	1243	2020	61.53465	0.7781	1	816	0	0.0000000	0.1224	34	4.1666667	0.6664	0	13	730	1.780822	0.5406	0	115	730	15.753425	0.8382	1	0	2020	0.0000	0.3640	0	2.70312	0.5665	1	3.27660	0.8614	3	0.7781	0.7709	1	2.5316	0.5047	1	9.28942	0.6832	6	1757	720	573	384	1511	25.41363	0.6427	0	29	717	4.044630	0.4132	0	33	392	8.418367	0.03542	0	116	181	64.08840	0.9086	1	149	573	26.00349	0.40410	0	139	1313	10.58644	0.5601	0	91	1533	5.936073	0.4343	0	284	16.163916	0.5169	0	325	18.49744	0.2851	0	164	1208.000	13.57616	0.4127	0	42	359.0000	11.699164	0.3998	0	0	1651	0.0000000	0.09479	1116	1757.000	63.51736	0.7591	1	720	3	0.4166667	0.2470	5	0.6944444	0.5106	0	9	573	1.5706806	0.4688	0	57	573.000	9.947644	0.7317	212	1757	12.0660216	0.9549	1	2.45440	0.4888	0	1.70929	0.1025	0	0.7591	0.7527	1	2.9130	0.6862	1	7.83579	0.4802	2	Yes
01001020700	01	001	020700	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	2664	1254	1139	710	2664	26.65165	0.6328	0	29	1310	2.213741	0.05255	0	134	710	18.87324	0.13890	187	429	43.58974	0.47090	321	1139	28.18262	0.28130	396	1852	21.38229	0.7478	0	345	2878	11.98749	0.4459	389	14.60210	0.6417	599	22.48499	0.4007	0	510	2168	23.52399	0.8752	1	228	712	32.022472	0.8712	1	0	2480	0.0000000	0.09298	694	2664	26.05105	0.5138	0	1254	8	0.6379585	0.2931	460	36.6826156	0.9714	1	0	1139	0.000000	0.1238	0	125	1139	10.974539	0.7477	0	0	2664	0.0000	0.3640	0	2.16035	0.4069	0	2.88178	0.6997	2	0.5138	0.5090	0	2.5000	0.4882	1	8.05593	0.5185	3	3562	1313	1248	1370	3528	38.83220	0.8512	1	128	1562	8.194622	0.7935	1	168	844	19.905213	0.44510	0	237	404	58.66337	0.8359	1	405	1248	32.45192	0.60420	0	396	2211	17.91045	0.7857	1	444	3547	12.517620	0.7758	1	355	9.966311	0.1800	0	954	26.78271	0.7923	1	629	2593.000	24.25762	0.8730	1	171	797.0000	21.455458	0.7186	0	0	3211	0.0000000	0.09479	1009	3562.000	28.32678	0.4668	0	1313	14	1.0662605	0.3165	443	33.7395278	0.9663	1	73	1248	5.8493590	0.8211	1	17	1248.000	1.362180	0.1554	112	3562	3.1443010	0.8514	1	3.81040	0.8569	4	2.65869	0.5847	2	0.4668	0.4629	0	3.1107	0.7714	3	10.04659	0.7851	9	Yes
01001021100	01	001	021100	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	3298	1502	1323	860	3298	26.07641	0.6211	0	297	1605	18.504673	0.94340	1	250	1016	24.60630	0.32070	74	307	24.10423	0.11920	324	1323	24.48980	0.17380	710	2231	31.82429	0.8976	1	654	3565	18.34502	0.7018	411	12.46210	0.5001	738	22.37720	0.3934	0	936	2861	32.71583	0.9807	1	138	825	16.727273	0.5715	0	9	3155	0.2852615	0.25010	1979	3298	60.00606	0.7703	1	1502	14	0.9320905	0.3234	659	43.8748336	0.9849	1	44	1323	3.325775	0.7062	0	137	1323	10.355253	0.7313	0	0	3298	0.0000	0.3640	0	3.33770	0.7351	2	2.69580	0.6028	1	0.7703	0.7631	1	3.1098	0.7827	1	9.91360	0.7557	5	3499	1825	1462	1760	3499	50.30009	0.9396	1	42	966	4.347826	0.4539	0	426	1274	33.437991	0.85200	1	52	188	27.65957	0.1824	0	478	1462	32.69494	0.61110	0	422	2488	16.96141	0.7638	1	497	3499	14.204058	0.8246	1	853	24.378394	0.8688	1	808	23.09231	0.5829	0	908	2691.100	33.74084	0.9808	1	179	811.6985	22.052524	0.7323	0	8	3248	0.2463054	0.26220	1986	3498.713	56.76373	0.7175	0	1825	29	1.5890411	0.3551	576	31.5616438	0.9594	1	88	1462	6.0191518	0.8269	1	148	1461.993	10.123166	0.7364	38	3499	1.0860246	0.7013	0	3.59300	0.8073	3	3.42700	0.9156	2	0.7175	0.7114	0	3.5791	0.9216	2	11.31660	0.9150	7	Yes
01003010200	01	003	010200	AL	Alabama	Baldwin County	3	South Region	6	East South Central Division	2612	1220	1074	338	2605	12.97505	0.2907	0	44	1193	3.688181	0.14720	0	172	928	18.53448	0.13090	31	146	21.23288	0.09299	203	1074	18.90130	0.05657	455	1872	24.30556	0.8016	1	456	2730	16.70330	0.6445	401	15.35222	0.6847	563	21.55436	0.3406	0	410	2038	20.11776	0.7755	1	64	779	8.215661	0.2181	0	0	2510	0.0000000	0.09298	329	2612	12.59571	0.3113	0	1220	38	3.1147541	0.4648	385	31.5573770	0.9545	1	20	1074	1.862197	0.5509	0	43	1074	4.003724	0.4088	0	0	2612	0.0000	0.3640	0	1.94057	0.3398	1	2.11188	0.2802	1	0.3113	0.3084	0	2.7430	0.6129	1	7.10675	0.3771	3	2928	1312	1176	884	2928	30.19126	0.7334	0	29	1459	1.987663	0.1356	0	71	830	8.554217	0.03726	0	134	346	38.72832	0.3964	0	205	1176	17.43197	0.12010	0	294	2052	14.32749	0.6940	0	219	2925	7.487179	0.5423	0	556	18.989071	0.6705	0	699	23.87295	0.6339	0	489	2226.455	21.96317	0.8122	1	191	783.8820	24.365914	0.7799	1	0	2710	0.0000000	0.09479	398	2927.519	13.59513	0.2511	0	1312	13	0.9908537	0.3111	400	30.4878049	0.9557	1	6	1176	0.5102041	0.2590	0	81	1176.202	6.886570	0.6115	7	2928	0.2390710	0.4961	0	2.22540	0.4183	0	2.99129	0.7634	2	0.2511	0.2490	0	2.6334	0.5496	1	8.10119	0.5207	3	Yes
01003010500	01	003	010500	AL	Alabama	Baldwin County	3	South Region	6	East South Central Division	4230	1779	1425	498	3443	14.46413	0.3337	0	166	1625	10.215385	0.71790	0	151	1069	14.12535	0.04638	196	356	55.05618	0.73830	347	1425	24.35088	0.17010	707	2945	24.00679	0.7967	1	528	4001	13.19670	0.5005	619	14.63357	0.6436	790	18.67612	0.1937	0	536	3096	17.31266	0.6572	0	165	920	17.934783	0.6102	0	20	4021	0.4973887	0.32320	754	4230	17.82506	0.4023	0	1779	97	5.4525014	0.5525	8	0.4496908	0.4600	0	63	1425	4.421053	0.7762	1	90	1425	6.315790	0.5691	0	787	4230	18.6052	0.9649	1	2.51890	0.5121	1	2.42790	0.4539	0	0.4023	0.3986	0	3.3227	0.8628	2	8.67180	0.6054	3	5877	1975	1836	820	5244	15.63692	0.3902	0	90	2583	3.484321	0.3361	0	159	1345	11.821561	0.10530	0	139	491	28.30957	0.1924	0	298	1836	16.23094	0.09053	0	570	4248	13.41808	0.6669	0	353	5247	6.727654	0.4924	0	1109	18.870172	0.6645	0	1144	19.46571	0.3411	0	717	4102.545	17.47696	0.6332	0	103	1286.1180	8.008596	0.2341	0	0	5639	0.0000000	0.09479	868	5877.481	14.76823	0.2709	0	1975	26	1.3164557	0.3359	45	2.2784810	0.6271	0	9	1836	0.4901961	0.2540	0	116	1835.798	6.318779	0.5811	633	5877	10.7708014	0.9507	1	1.97613	0.3410	0	1.96769	0.1961	0	0.2709	0.2686	0	2.7488	0.6077	1	6.96352	0.3406	1	Yes
01003010600	01	003	010600	AL	Alabama	Baldwin County	3	South Region	6	East South Central Division	3724	1440	1147	1973	3724	52.98067	0.9342	1	142	1439	9.867964	0.69680	0	235	688	34.15698	0.62950	187	459	40.74074	0.40290	422	1147	36.79163	0.55150	497	1876	26.49254	0.8354	1	511	3661	13.95794	0.5334	246	6.60580	0.1481	1256	33.72718	0.9305	1	496	2522	19.66693	0.7587	1	274	838	32.696897	0.8779	1	32	3479	0.9198045	0.42810	2606	3724	69.97852	0.8184	1	1440	21	1.4583333	0.3683	321	22.2916667	0.9036	1	97	1147	8.456844	0.8956	1	167	1147	14.559721	0.8209	1	0	3724	0.0000	0.3640	0	3.55130	0.7859	2	3.14330	0.8145	3	0.8184	0.8108	1	3.3524	0.8725	3	10.86540	0.8550	9	4115	1534	1268	1676	3997	41.93145	0.8814	1	294	1809	16.252073	0.9674	1	341	814	41.891892	0.94320	1	204	454	44.93392	0.5438	0	545	1268	42.98107	0.83620	1	624	2425	25.73196	0.9002	1	994	4115	24.155529	0.9602	1	642	15.601458	0.4841	0	1126	27.36331	0.8175	1	568	2989.000	19.00301	0.7045	0	212	715.0000	29.650350	0.8592	1	56	3825	1.4640523	0.53120	2715	4115.000	65.97813	0.7732	1	1534	0	0.0000000	0.1079	529	34.4850065	0.9685	1	101	1268	7.9652997	0.8795	1	89	1268.000	7.018927	0.6184	17	4115	0.4131227	0.5707	0	4.54540	0.9754	5	3.39650	0.9081	2	0.7732	0.7667	1	3.1450	0.7858	2	11.86010	0.9520	10	Yes

Find count of pre2010 NMTC projects:

Code

# Join divisional data to nmtc_awards_pre2010, set count to 0 if no data
svi_divisional_nmtc_eligible <- 
  left_join(svi_divisional_nmtc_eligible, nmtc_awards_pre2010, join_by("GEOID_2010_trt" == "GEOID10")) %>%
  mutate(pre10_nmtc_project_cnt = if_else(is.na(pre10_nmtc_project_cnt), 0, pre10_nmtc_project_cnt)) %>%
    mutate(pre10_nmtc_dollars = if_else(is.na(pre10_nmtc_dollars), 0, pre10_nmtc_dollars)) %>%
    mutate(pre10_nmtc_dollars_formatted = if_else(is.na(pre10_nmtc_dollars_formatted), "$0", pre10_nmtc_dollars_formatted))

# View table
svi_divisional_nmtc_eligible %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID_2010_trt	FIPS_st	FIPS_county	FIPS_tract	state	state_name	county	region_number	region	division_number	division	E_TOTPOP_10	E_HU_10	E_HH_10	E_POV150_10	ET_POVSTATUS_10	EP_POV150_10	EPL_POV150_10	F_POV150_10	E_UNEMP_10	ET_EMPSTATUS_10	EP_UNEMP_10	EPL_UNEMP_10	F_UNEMP_10	E_HBURD_OWN_10	ET_HOUSINGCOST_OWN_10	EP_HBURD_OWN_10	EPL_HBURD_OWN_10	F_HBURD_OWN_10	E_HBURD_RENT_10	ET_HOUSINGCOST_RENT_10	EP_HBURD_RENT_10	EPL_HBURD_RENT_10	F_HBURD_RENT_10	E_HBURD_10	ET_HOUSINGCOST_10	EP_HBURD_10	EPL_HBURD_10	F_HBURD_10	E_NOHSDP_10	ET_EDSTATUS_10	EP_NOHSDP_10	EPL_NOHSDP_10	F_NOHSDP_10	E_UNINSUR_12	ET_INSURSTATUS_12	EP_UNINSUR_12	EPL_UNINSUR_12	F_UNINSUR_12	E_AGE65_10	EP_AGE65_10	EPL_AGE65_10	F_AGE65_10	E_AGE17_10	EP_AGE17_10	EPL_AGE17_10	F_AGE17_10	E_DISABL_12	ET_DISABLSTATUS_12	EP_DISABL_12	EPL_DISABL_12	F_DISABL_12	E_SNGPNT_10	ET_FAMILIES_10	EP_SNGPNT_10	EPL_SNGPNT_10	F_SNGPNT_10	E_LIMENG_10	ET_POPAGE5UP_10	EP_LIMENG_10	EPL_LIMENG_10	F_LIMENG_10	E_MINRTY_10	ET_POPETHRACE_10	EP_MINRTY_10	EPL_MINRTY_10	F_MINRTY_10	E_STRHU_10	E_MUNIT_10	EP_MUNIT_10	EPL_MUNIT_10	F_MUNIT_10	E_MOBILE_10	EP_MOBILE_10	EPL_MOBILE_10	E_CROWD_10	ET_OCCUPANTS_10	EP_CROWD_10	EPL_CROWD_10	F_CROWD_10	E_NOVEH_10	ET_KNOWNVEH_10	EP_NOVEH_10	EPL_NOVEH_10	F_NOVEH_10	E_GROUPQ_10	ET_HHTYPE_10	EP_GROUPQ_10	EPL_GROUPQ_10	F_GROUPQ_10	SPL_THEME1_10	RPL_THEME1_10	F_THEME1_10	SPL_THEME2_10	RPL_THEME2_10	F_THEME2_10	SPL_THEME3_10	RPL_THEME3_10	F_THEME3_10	SPL_THEME4_10	RPL_THEME4_10	F_THEME4_10	SPL_THEMES_10	RPL_THEMES_10	F_TOTAL_10	E_TOTPOP_20	E_HU_20	E_HH_20	E_POV150_20	ET_POVSTATUS_20	EP_POV150_20	EPL_POV150_20	F_POV150_20	E_UNEMP_20	ET_EMPSTATUS_20	EP_UNEMP_20	EPL_UNEMP_20	F_UNEMP_20	E_HBURD_OWN_20	ET_HOUSINGCOST_OWN_20	EP_HBURD_OWN_20	EPL_HBURD_OWN_20	F_HBURD_OWN_20	E_HBURD_RENT_20	ET_HOUSINGCOST_RENT_20	EP_HBURD_RENT_20	EPL_HBURD_RENT_20	F_HBURD_RENT_20	E_HBURD_20	ET_HOUSINGCOST_20	EP_HBURD_20	EPL_HBURD_20	F_HBURD_20	E_NOHSDP_20	ET_EDSTATUS_20	EP_NOHSDP_20	EPL_NOHSDP_20	F_NOHSDP_20	E_UNINSUR_20	ET_INSURSTATUS_20	EP_UNINSUR_20	EPL_UNINSUR_20	F_UNINSUR_20	E_AGE65_20	EP_AGE65_20	EPL_AGE65_20	E_AGE17_20	EP_AGE17_20	EPL_AGE17_20	F_AGE17_20	E_DISABL_20	ET_DISABLSTATUS_20	EP_DISABL_20	EPL_DISABL_20	F_DISABL_20	E_SNGPNT_20	ET_FAMILIES_20	EP_SNGPNT_20	EPL_SNGPNT_20	F_SNGPNT_20	E_LIMENG_20	ET_POPAGE5UP_20	EP_LIMENG_20	EPL_LIMENG_20	F_LIMENG_20	E_MINRTY_20	ET_POPETHRACE_20	EP_MINRTY_20	EPL_MINRTY_20	F_MINRTY_20	E_STRHU_20	E_MUNIT_20	EP_MUNIT_20	EPL_MUNIT_20	F_MUNIT_20	E_MOBILE_20	EP_MOBILE_20	EPL_MOBILE_20	E_CROWD_20	ET_OCCUPANTS_20	EP_CROWD_20	EPL_CROWD_20	F_CROWD_20	E_NOVEH_20	ET_KNOWNVEH_20	EP_NOVEH_20	EPL_NOVEH_20	F_NOVEH_20	E_GROUPQ_20	ET_HHTYPE_20	EP_GROUPQ_20	EPL_GROUPQ_20	SPL_THEME1_20	RPL_THEME1_20	F_THEME1_20	SPL_THEME2_20	RPL_THEME2_20	F_THEME2_20	SPL_THEME3_20	RPL_THEME3_20	F_THEME3_20	SPL_THEME4_20	RPL_THEME4_20	F_THEME4_20	SPL_THEMES_20	RPL_THEMES_20	F_TOTAL_20	nmtc_eligibility	pre10_nmtc_project_cnt	pre10_nmtc_dollars	pre10_nmtc_dollars_formatted
34001000100	34	001	000100	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2907	1088	983	1127	2907	38.76849	0.8482	1	144	1433	10.048849	0.7544	1	280	435	64.36782	0.9529	1	204	548	37.22628	0.2998	0	484	983	49.23703	0.7813	1	468	1759	26.60603	0.8634	1	532	2543	20.92017	0.8978	1	250	8.599931	0.1777	0	944	32.47334	0.94170	1	186	1851	10.04862	0.2706	0	266	678	39.233038	0.8981	1	177	2611	6.779012	0.7778	1	1928	2907	66.32267	0.7743	1	1088	113	10.386029	0.6229	0	9	0.8272059	0.7223	80	983	8.138352	0.8657	1	265	983	26.95829	0.7354	0	0	2907	0.000000	0.3512	0	4.1451	0.8935	5	3.06590	0.7944	3	0.7743	0.7667	1	3.2975	0.8414	1	11.28280	0.8862	10	2157	941	784	1182	2157	54.79833	0.9571	1	242	1058	22.873346	0.9922	1	215	342	62.86550	0.9780	1	316	442	71.49321	0.9481	1	531	784	67.72959	0.9893	1	396	1274	31.08320	0.9497	1	266	2157	12.331943	0.9041	1	185	8.576727	0.09430	552	25.59110	0.8128	1	297	1605	18.504673	0.74880	0	83	510	16.27451	0.6090	0	251	2020	12.425743	0.8710	1	1852	2157	85.85999	0.8476	1	941	118	12.5398512	0.6385	0	0	0.0000000	0.3216	67	784	8.545918	0.8657	1	212	784	27.04082	0.7502	1	0	2157	0.0000000	0.1517	4.7924	0.9850	5	3.13590	0.8217	2	0.8476	0.8400	1	2.7277	0.6085	2	11.50360	0.9104	10	Yes	0	0	$0
34001000200	34	001	000200	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3189	2217	1473	519	3189	16.27469	0.4806	0	109	1558	6.996149	0.5179	0	573	955	60.00000	0.9323	1	199	518	38.41699	0.3261	0	772	1473	52.41005	0.8418	1	405	2579	15.70376	0.6491	0	484	3547	13.64533	0.7154	0	847	26.560050	0.9629	1	436	13.67200	0.08181	0	608	3005	20.23295	0.8466	1	42	857	4.900817	0.1204	0	422	3072	13.736979	0.8799	1	1792	3189	56.19316	0.7390	0	2217	901	40.640505	0.8693	1	0	0.0000000	0.3251	48	1473	3.258656	0.7064	0	250	1473	16.97217	0.6444	0	0	3189	0.000000	0.3512	0	3.2048	0.6963	1	2.89161	0.7231	3	0.7390	0.7317	0	2.8964	0.6887	1	9.73181	0.7340	5	3510	2046	1353	1021	3510	29.08832	0.7682	1	121	1852	6.533477	0.6717	0	343	696	49.28161	0.9273	1	416	657	63.31811	0.8696	1	759	1353	56.09756	0.9321	1	553	2338	23.65269	0.8871	1	354	3510	10.085470	0.8530	1	643	18.319088	0.60310	1002	28.54701	0.9055	1	450	2508	17.942584	0.72330	0	237	786	30.15267	0.8539	1	534	3375	15.822222	0.9062	1	2534	3510	72.19373	0.7818	1	2046	906	44.2815249	0.8690	1	0	0.0000000	0.3216	119	1353	8.795270	0.8711	1	324	1353	23.94678	0.7255	0	0	3510	0.0000000	0.1517	4.1121	0.9003	4	3.99200	0.9781	3	0.7818	0.7747	1	2.9389	0.7011	2	11.82480	0.9310	10	Yes	0	0	$0
34001000300	34	001	000300	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3997	1823	1357	1401	3968	35.30746	0.8164	1	382	2238	17.068811	0.9376	1	176	329	53.49544	0.8855	1	604	1028	58.75486	0.7947	1	780	1357	57.47973	0.9165	1	920	2677	34.36683	0.9346	1	1351	4149	32.56206	0.9811	1	314	7.855892	0.1437	0	937	23.44258	0.55900	0	319	3054	10.44532	0.3000	0	187	782	23.913044	0.7498	0	1080	3671	29.419777	0.9742	1	3357	3997	83.98799	0.8419	1	1823	363	19.912233	0.7535	1	0	0.0000000	0.3251	150	1357	11.053795	0.9136	1	651	1357	47.97347	0.8585	1	0	3997	0.000000	0.3512	0	4.5862	0.9691	5	2.72670	0.6360	1	0.8419	0.8336	1	3.2019	0.8054	3	11.35670	0.8920	10	3801	1640	1226	1857	3801	48.85556	0.9333	1	226	1800	12.555556	0.9267	1	111	280	39.64286	0.8339	1	608	946	64.27061	0.8842	1	719	1226	58.64600	0.9528	1	650	2275	28.57143	0.9337	1	1027	3801	27.019206	0.9914	1	380	9.997369	0.14040	1223	32.17574	0.9607	1	219	2578	8.494957	0.15680	0	268	909	29.48295	0.8456	1	940	3400	27.647059	0.9728	1	3318	3801	87.29282	0.8579	1	1640	262	15.9756098	0.6917	0	0	0.0000000	0.3216	124	1226	10.114192	0.8955	1	477	1226	38.90701	0.8258	1	0	3801	0.0000000	0.1517	4.7379	0.9829	5	3.07630	0.8013	3	0.8579	0.8501	1	2.8863	0.6781	2	11.55840	0.9150	11	Yes	0	0	$0
34001000400	34	001	000400	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2902	2683	1401	1172	2902	40.38594	0.8615	1	190	1389	13.678906	0.8811	1	364	707	51.48515	0.8627	1	507	694	73.05476	0.9503	1	871	1401	62.16988	0.9572	1	481	1981	24.28067	0.8339	1	674	3204	21.03620	0.8998	1	434	14.955203	0.6083	0	596	20.53756	0.33980	0	426	2607	16.34062	0.6886	0	111	652	17.024540	0.6204	0	215	2736	7.858187	0.8008	1	1792	2902	61.75052	0.7584	1	2683	2049	76.369735	0.9401	1	0	0.0000000	0.3251	69	1401	4.925053	0.7847	1	511	1401	36.47395	0.7992	1	72	2902	2.481048	0.8114	1	4.4335	0.9468	5	3.05790	0.7908	1	0.7584	0.7510	1	3.6605	0.9391	4	11.91030	0.9339	11	3178	2264	1390	1508	3176	47.48111	0.9246	1	172	1804	9.534368	0.8460	1	205	468	43.80342	0.8858	1	622	922	67.46204	0.9192	1	827	1390	59.49640	0.9587	1	364	2076	17.53372	0.8013	1	476	3178	14.977974	0.9390	1	483	15.198238	0.41220	539	16.96035	0.2484	0	319	2639	12.087912	0.38790	0	101	565	17.87611	0.6539	0	583	3022	19.291860	0.9349	1	2186	3178	68.78540	0.7658	1	2264	1609	71.0689046	0.9266	1	15	0.6625442	0.7078	226	1390	16.258993	0.9567	1	599	1390	43.09353	0.8474	1	20	3178	0.6293266	0.6292	4.4696	0.9558	5	2.63730	0.5864	1	0.7658	0.7588	1	4.0677	0.9762	3	11.94040	0.9387	10	Yes	1	4200000	$4,200,000
34001000500	34	001	000500	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3483	1241	1027	1938	3483	55.64169	0.9533	1	124	1630	7.607362	0.5830	0	227	446	50.89686	0.8549	1	478	581	82.27194	0.9799	1	705	1027	68.64654	0.9863	1	733	2077	35.29129	0.9396	1	727	3258	22.31430	0.9149	1	377	10.824002	0.3081	0	1055	30.28998	0.90140	1	268	2401	11.16202	0.3549	0	209	763	27.391874	0.7940	1	911	3077	29.606760	0.9746	1	3036	3483	87.16624	0.8550	1	1241	52	4.190169	0.4505	0	4	0.3223207	0.6567	113	1027	11.002921	0.9128	1	422	1027	41.09056	0.8250	1	0	3483	0.000000	0.3512	0	4.3771	0.9379	4	3.33300	0.8766	3	0.8550	0.8467	1	3.1962	0.8026	2	11.76130	0.9229	10	3385	1185	945	1682	3364	50.00000	0.9391	1	72	1577	4.565631	0.4586	0	185	468	39.52991	0.8332	1	362	477	75.89099	0.9703	1	547	945	57.88360	0.9477	1	592	1983	29.85376	0.9422	1	738	3385	21.802068	0.9817	1	240	7.090103	0.05988	1129	33.35303	0.9689	1	135	2256	5.984043	0.04817	0	110	717	15.34170	0.5822	0	721	3076	23.439532	0.9569	1	3029	3385	89.48301	0.8727	1	1185	9	0.7594937	0.2382	0	0	0.0000000	0.3216	103	945	10.899471	0.9072	1	263	945	27.83069	0.7560	1	0	3385	0.0000000	0.1517	4.2693	0.9283	4	2.61605	0.5709	2	0.8727	0.8648	1	2.3747	0.4357	2	10.13275	0.7921	9	Yes	0	0	$0
34001001100	34	001	001100	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2204	1204	1204	1185	2204	53.76588	0.9457	1	219	927	23.624596	0.9830	1	97	172	56.39535	0.9094	1	462	1032	44.76744	0.4746	0	559	1204	46.42857	0.7197	0	346	1440	24.02778	0.8306	1	469	1942	24.15036	0.9360	1	363	16.470054	0.7020	0	578	26.22505	0.74410	0	442	1558	28.36970	0.9675	1	247	396	62.373737	0.9898	1	104	2051	5.070697	0.7260	0	2118	2204	96.09800	0.9204	1	1204	570	47.342193	0.8858	1	0	0.0000000	0.3251	14	1204	1.162791	0.4877	0	817	1204	67.85714	0.9413	1	0	2204	0.000000	0.3512	0	4.4150	0.9451	4	4.12940	0.9805	2	0.9204	0.9114	1	2.9911	0.7243	2	12.45590	0.9597	9	1950	1267	1096	1131	1950	58.00000	0.9678	1	66	706	9.348442	0.8395	1	42	101	41.58416	0.8612	1	309	995	31.05528	0.1959	0	351	1096	32.02555	0.4782	0	510	1379	36.98332	0.9763	1	155	1950	7.948718	0.7660	1	392	20.102564	0.69880	447	22.92308	0.6712	0	570	1503	37.924152	0.99200	1	143	374	38.23529	0.9167	1	109	1841	5.920695	0.7464	0	1909	1950	97.89744	0.9529	1	1267	479	37.8058406	0.8464	1	0	0.0000000	0.3216	33	1096	3.010949	0.6446	0	743	1096	67.79197	0.9414	1	0	1950	0.0000000	0.1517	4.0278	0.8848	4	4.02510	0.9798	2	0.9529	0.9442	1	2.9057	0.6869	2	11.91150	0.9365	9	Yes	0	0	$0

Code

# Join national data to nmtc_awards_pre2010, set count to 0 if no data
svi_national_nmtc_eligible <- 
  left_join(svi_national_nmtc_eligible, nmtc_awards_pre2010, join_by("GEOID_2010_trt" == "GEOID10")) %>%
  mutate(pre10_nmtc_project_cnt = if_else(is.na(pre10_nmtc_project_cnt), 0, pre10_nmtc_project_cnt)) %>%
    mutate(pre10_nmtc_dollars = if_else(is.na(pre10_nmtc_dollars), 0, pre10_nmtc_dollars))%>%
    mutate(pre10_nmtc_dollars_formatted = if_else(is.na(pre10_nmtc_dollars_formatted), "$0", pre10_nmtc_dollars_formatted))

# View table
svi_national_nmtc_eligible %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID_2010_trt	FIPS_st	FIPS_county	FIPS_tract	state	state_name	county	region_number	region	division_number	division	E_TOTPOP_10	E_HU_10	E_HH_10	E_POV150_10	ET_POVSTATUS_10	EP_POV150_10	EPL_POV150_10	F_POV150_10	E_UNEMP_10	ET_EMPSTATUS_10	EP_UNEMP_10	EPL_UNEMP_10	F_UNEMP_10	E_HBURD_OWN_10	ET_HOUSINGCOST_OWN_10	EP_HBURD_OWN_10	EPL_HBURD_OWN_10	E_HBURD_RENT_10	ET_HOUSINGCOST_RENT_10	EP_HBURD_RENT_10	EPL_HBURD_RENT_10	E_HBURD_10	ET_HOUSINGCOST_10	EP_HBURD_10	EPL_HBURD_10	E_NOHSDP_10	ET_EDSTATUS_10	EP_NOHSDP_10	EPL_NOHSDP_10	F_NOHSDP_10	E_UNINSUR_12	ET_INSURSTATUS_12	EP_UNINSUR_12	EPL_UNINSUR_12	E_AGE65_10	EP_AGE65_10	EPL_AGE65_10	E_AGE17_10	EP_AGE17_10	EPL_AGE17_10	F_AGE17_10	E_DISABL_12	ET_DISABLSTATUS_12	EP_DISABL_12	EPL_DISABL_12	F_DISABL_12	E_SNGPNT_10	ET_FAMILIES_10	EP_SNGPNT_10	EPL_SNGPNT_10	F_SNGPNT_10	E_LIMENG_10	ET_POPAGE5UP_10	EP_LIMENG_10	EPL_LIMENG_10	E_MINRTY_10	ET_POPETHRACE_10	EP_MINRTY_10	EPL_MINRTY_10	F_MINRTY_10	E_STRHU_10	E_MUNIT_10	EP_MUNIT_10	EPL_MUNIT_10	E_MOBILE_10	EP_MOBILE_10	EPL_MOBILE_10	F_MOBILE_10	E_CROWD_10	ET_OCCUPANTS_10	EP_CROWD_10	EPL_CROWD_10	F_CROWD_10	E_NOVEH_10	ET_KNOWNVEH_10	EP_NOVEH_10	EPL_NOVEH_10	F_NOVEH_10	E_GROUPQ_10	ET_HHTYPE_10	EP_GROUPQ_10	EPL_GROUPQ_10	F_GROUPQ_10	SPL_THEME1_10	RPL_THEME1_10	F_THEME1_10	SPL_THEME2_10	RPL_THEME2_10	F_THEME2_10	SPL_THEME3_10	RPL_THEME3_10	F_THEME3_10	SPL_THEME4_10	RPL_THEME4_10	F_THEME4_10	SPL_THEMES_10	RPL_THEMES_10	F_TOTAL_10	E_TOTPOP_20	E_HU_20	E_HH_20	E_POV150_20	ET_POVSTATUS_20	EP_POV150_20	EPL_POV150_20	F_POV150_20	E_UNEMP_20	ET_EMPSTATUS_20	EP_UNEMP_20	EPL_UNEMP_20	F_UNEMP_20	E_HBURD_OWN_20	ET_HOUSINGCOST_OWN_20	EP_HBURD_OWN_20	EPL_HBURD_OWN_20	F_HBURD_OWN_20	E_HBURD_RENT_20	ET_HOUSINGCOST_RENT_20	EP_HBURD_RENT_20	EPL_HBURD_RENT_20	F_HBURD_RENT_20	E_HBURD_20	ET_HOUSINGCOST_20	EP_HBURD_20	EPL_HBURD_20	F_HBURD_20	E_NOHSDP_20	ET_EDSTATUS_20	EP_NOHSDP_20	EPL_NOHSDP_20	F_NOHSDP_20	E_UNINSUR_20	ET_INSURSTATUS_20	EP_UNINSUR_20	EPL_UNINSUR_20	F_UNINSUR_20	E_AGE65_20	EP_AGE65_20	EPL_AGE65_20	F_AGE65_20	E_AGE17_20	EP_AGE17_20	EPL_AGE17_20	F_AGE17_20	E_DISABL_20	ET_DISABLSTATUS_20	EP_DISABL_20	EPL_DISABL_20	F_DISABL_20	E_SNGPNT_20	ET_FAMILIES_20	EP_SNGPNT_20	EPL_SNGPNT_20	F_SNGPNT_20	E_LIMENG_20	ET_POPAGE5UP_20	EP_LIMENG_20	EPL_LIMENG_20	E_MINRTY_20	ET_POPETHRACE_20	EP_MINRTY_20	EPL_MINRTY_20	F_MINRTY_20	E_STRHU_20	E_MUNIT_20	EP_MUNIT_20	EPL_MUNIT_20	E_MOBILE_20	EP_MOBILE_20	EPL_MOBILE_20	F_MOBILE_20	E_CROWD_20	ET_OCCUPANTS_20	EP_CROWD_20	EPL_CROWD_20	F_CROWD_20	E_NOVEH_20	ET_KNOWNVEH_20	EP_NOVEH_20	EPL_NOVEH_20	E_GROUPQ_20	ET_HHTYPE_20	EP_GROUPQ_20	EPL_GROUPQ_20	F_GROUPQ_20	SPL_THEME1_20	RPL_THEME1_20	F_THEME1_20	SPL_THEME2_20	RPL_THEME2_20	F_THEME2_20	SPL_THEME3_20	RPL_THEME3_20	F_THEME3_20	SPL_THEME4_20	RPL_THEME4_20	F_THEME4_20	SPL_THEMES_20	RPL_THEMES_20	F_TOTAL_20	nmtc_eligibility	pre10_nmtc_dollars_formatted
01001020200	01	001	020200	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	2020	816	730	495	1992	24.84940	0.5954	0	68	834	8.153477	0.57540	0	49	439	11.16173	0.02067	105	291	36.08247	0.30190	154	730	21.09589	0.09312	339	1265	26.79842	0.8392	1	313	2012	15.55666	0.6000	204	10.09901	0.3419	597	29.55446	0.8192	1	359	1515	23.69637	0.8791	1	132	456	28.947368	0.8351	1	15	1890	0.7936508	0.40130	1243	2020	61.53465	0.7781	1	816	0	0.0000000	0.1224	34	4.1666667	0.6664	0	13	730	1.780822	0.5406	0	115	730	15.753425	0.8382	1	0	2020	0.0000	0.3640	0	2.70312	0.5665	1	3.27660	0.8614	3	0.7781	0.7709	1	2.5316	0.5047	1	9.28942	0.6832	6	1757	720	573	384	1511	25.41363	0.6427	0	29	717	4.044630	0.4132	0	33	392	8.418367	0.03542	0	116	181	64.08840	0.9086	1	149	573	26.00349	0.40410	0	139	1313	10.58644	0.5601	0	91	1533	5.936073	0.4343	0	284	16.163916	0.5169	0	325	18.49744	0.2851	0	164	1208.000	13.57616	0.4127	0	42	359.0000	11.699164	0.3998	0	0	1651	0.0000000	0.09479	1116	1757.000	63.51736	0.7591	1	720	3	0.4166667	0.2470	5	0.6944444	0.5106	0	9	573	1.5706806	0.4688	0	57	573.000	9.947644	0.7317	212	1757	12.0660216	0.9549	1	2.45440	0.4888	0	1.70929	0.1025	0	0.7591	0.7527	1	2.9130	0.6862	1	7.83579	0.4802	2	Yes	$0
01001020700	01	001	020700	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	2664	1254	1139	710	2664	26.65165	0.6328	0	29	1310	2.213741	0.05255	0	134	710	18.87324	0.13890	187	429	43.58974	0.47090	321	1139	28.18262	0.28130	396	1852	21.38229	0.7478	0	345	2878	11.98749	0.4459	389	14.60210	0.6417	599	22.48499	0.4007	0	510	2168	23.52399	0.8752	1	228	712	32.022472	0.8712	1	0	2480	0.0000000	0.09298	694	2664	26.05105	0.5138	0	1254	8	0.6379585	0.2931	460	36.6826156	0.9714	1	0	1139	0.000000	0.1238	0	125	1139	10.974539	0.7477	0	0	2664	0.0000	0.3640	0	2.16035	0.4069	0	2.88178	0.6997	2	0.5138	0.5090	0	2.5000	0.4882	1	8.05593	0.5185	3	3562	1313	1248	1370	3528	38.83220	0.8512	1	128	1562	8.194622	0.7935	1	168	844	19.905213	0.44510	0	237	404	58.66337	0.8359	1	405	1248	32.45192	0.60420	0	396	2211	17.91045	0.7857	1	444	3547	12.517620	0.7758	1	355	9.966311	0.1800	0	954	26.78271	0.7923	1	629	2593.000	24.25762	0.8730	1	171	797.0000	21.455458	0.7186	0	0	3211	0.0000000	0.09479	1009	3562.000	28.32678	0.4668	0	1313	14	1.0662605	0.3165	443	33.7395278	0.9663	1	73	1248	5.8493590	0.8211	1	17	1248.000	1.362180	0.1554	112	3562	3.1443010	0.8514	1	3.81040	0.8569	4	2.65869	0.5847	2	0.4668	0.4629	0	3.1107	0.7714	3	10.04659	0.7851	9	Yes	$0
01001021100	01	001	021100	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	3298	1502	1323	860	3298	26.07641	0.6211	0	297	1605	18.504673	0.94340	1	250	1016	24.60630	0.32070	74	307	24.10423	0.11920	324	1323	24.48980	0.17380	710	2231	31.82429	0.8976	1	654	3565	18.34502	0.7018	411	12.46210	0.5001	738	22.37720	0.3934	0	936	2861	32.71583	0.9807	1	138	825	16.727273	0.5715	0	9	3155	0.2852615	0.25010	1979	3298	60.00606	0.7703	1	1502	14	0.9320905	0.3234	659	43.8748336	0.9849	1	44	1323	3.325775	0.7062	0	137	1323	10.355253	0.7313	0	0	3298	0.0000	0.3640	0	3.33770	0.7351	2	2.69580	0.6028	1	0.7703	0.7631	1	3.1098	0.7827	1	9.91360	0.7557	5	3499	1825	1462	1760	3499	50.30009	0.9396	1	42	966	4.347826	0.4539	0	426	1274	33.437991	0.85200	1	52	188	27.65957	0.1824	0	478	1462	32.69494	0.61110	0	422	2488	16.96141	0.7638	1	497	3499	14.204058	0.8246	1	853	24.378394	0.8688	1	808	23.09231	0.5829	0	908	2691.100	33.74084	0.9808	1	179	811.6985	22.052524	0.7323	0	8	3248	0.2463054	0.26220	1986	3498.713	56.76373	0.7175	0	1825	29	1.5890411	0.3551	576	31.5616438	0.9594	1	88	1462	6.0191518	0.8269	1	148	1461.993	10.123166	0.7364	38	3499	1.0860246	0.7013	0	3.59300	0.8073	3	3.42700	0.9156	2	0.7175	0.7114	0	3.5791	0.9216	2	11.31660	0.9150	7	Yes	$0
01003010200	01	003	010200	AL	Alabama	Baldwin County	3	South Region	6	East South Central Division	2612	1220	1074	338	2605	12.97505	0.2907	0	44	1193	3.688181	0.14720	0	172	928	18.53448	0.13090	31	146	21.23288	0.09299	203	1074	18.90130	0.05657	455	1872	24.30556	0.8016	1	456	2730	16.70330	0.6445	401	15.35222	0.6847	563	21.55436	0.3406	0	410	2038	20.11776	0.7755	1	64	779	8.215661	0.2181	0	0	2510	0.0000000	0.09298	329	2612	12.59571	0.3113	0	1220	38	3.1147541	0.4648	385	31.5573770	0.9545	1	20	1074	1.862197	0.5509	0	43	1074	4.003724	0.4088	0	0	2612	0.0000	0.3640	0	1.94057	0.3398	1	2.11188	0.2802	1	0.3113	0.3084	0	2.7430	0.6129	1	7.10675	0.3771	3	2928	1312	1176	884	2928	30.19126	0.7334	0	29	1459	1.987663	0.1356	0	71	830	8.554217	0.03726	0	134	346	38.72832	0.3964	0	205	1176	17.43197	0.12010	0	294	2052	14.32749	0.6940	0	219	2925	7.487179	0.5423	0	556	18.989071	0.6705	0	699	23.87295	0.6339	0	489	2226.455	21.96317	0.8122	1	191	783.8820	24.365914	0.7799	1	0	2710	0.0000000	0.09479	398	2927.519	13.59513	0.2511	0	1312	13	0.9908537	0.3111	400	30.4878049	0.9557	1	6	1176	0.5102041	0.2590	0	81	1176.202	6.886570	0.6115	7	2928	0.2390710	0.4961	0	2.22540	0.4183	0	2.99129	0.7634	2	0.2511	0.2490	0	2.6334	0.5496	1	8.10119	0.5207	3	Yes	$0
01003010500	01	003	010500	AL	Alabama	Baldwin County	3	South Region	6	East South Central Division	4230	1779	1425	498	3443	14.46413	0.3337	0	166	1625	10.215385	0.71790	0	151	1069	14.12535	0.04638	196	356	55.05618	0.73830	347	1425	24.35088	0.17010	707	2945	24.00679	0.7967	1	528	4001	13.19670	0.5005	619	14.63357	0.6436	790	18.67612	0.1937	0	536	3096	17.31266	0.6572	0	165	920	17.934783	0.6102	0	20	4021	0.4973887	0.32320	754	4230	17.82506	0.4023	0	1779	97	5.4525014	0.5525	8	0.4496908	0.4600	0	63	1425	4.421053	0.7762	1	90	1425	6.315790	0.5691	0	787	4230	18.6052	0.9649	1	2.51890	0.5121	1	2.42790	0.4539	0	0.4023	0.3986	0	3.3227	0.8628	2	8.67180	0.6054	3	5877	1975	1836	820	5244	15.63692	0.3902	0	90	2583	3.484321	0.3361	0	159	1345	11.821561	0.10530	0	139	491	28.30957	0.1924	0	298	1836	16.23094	0.09053	0	570	4248	13.41808	0.6669	0	353	5247	6.727654	0.4924	0	1109	18.870172	0.6645	0	1144	19.46571	0.3411	0	717	4102.545	17.47696	0.6332	0	103	1286.1180	8.008596	0.2341	0	0	5639	0.0000000	0.09479	868	5877.481	14.76823	0.2709	0	1975	26	1.3164557	0.3359	45	2.2784810	0.6271	0	9	1836	0.4901961	0.2540	0	116	1835.798	6.318779	0.5811	633	5877	10.7708014	0.9507	1	1.97613	0.3410	0	1.96769	0.1961	0	0.2709	0.2686	0	2.7488	0.6077	1	6.96352	0.3406	1	Yes	$0
01003010600	01	003	010600	AL	Alabama	Baldwin County	3	South Region	6	East South Central Division	3724	1440	1147	1973	3724	52.98067	0.9342	1	142	1439	9.867964	0.69680	0	235	688	34.15698	0.62950	187	459	40.74074	0.40290	422	1147	36.79163	0.55150	497	1876	26.49254	0.8354	1	511	3661	13.95794	0.5334	246	6.60580	0.1481	1256	33.72718	0.9305	1	496	2522	19.66693	0.7587	1	274	838	32.696897	0.8779	1	32	3479	0.9198045	0.42810	2606	3724	69.97852	0.8184	1	1440	21	1.4583333	0.3683	321	22.2916667	0.9036	1	97	1147	8.456844	0.8956	1	167	1147	14.559721	0.8209	1	0	3724	0.0000	0.3640	0	3.55130	0.7859	2	3.14330	0.8145	3	0.8184	0.8108	1	3.3524	0.8725	3	10.86540	0.8550	9	4115	1534	1268	1676	3997	41.93145	0.8814	1	294	1809	16.252073	0.9674	1	341	814	41.891892	0.94320	1	204	454	44.93392	0.5438	0	545	1268	42.98107	0.83620	1	624	2425	25.73196	0.9002	1	994	4115	24.155529	0.9602	1	642	15.601458	0.4841	0	1126	27.36331	0.8175	1	568	2989.000	19.00301	0.7045	0	212	715.0000	29.650350	0.8592	1	56	3825	1.4640523	0.53120	2715	4115.000	65.97813	0.7732	1	1534	0	0.0000000	0.1079	529	34.4850065	0.9685	1	101	1268	7.9652997	0.8795	1	89	1268.000	7.018927	0.6184	17	4115	0.4131227	0.5707	0	4.54540	0.9754	5	3.39650	0.9081	2	0.7732	0.7667	1	3.1450	0.7858	2	11.86010	0.9520	10	Yes	$0

Check row count:

Code

# See number of rows
svi_divisional_nmtc_eligible %>% nrow()

[1] 3920

Code

# See number of rows
svi_national_nmtc_eligible %>% nrow()

[1] 30847

Finally, we need to filter our data set to exclude tracts without SVI flag data for 2010 and/or 2020 (population may be too small), we also need to exclude tracts that had an NMTC project before 2010 since we want to measure the impact of the introduction of NMTC projects. We will discuss this more in-depth in Lab 05, but broadly we want to ensure that previous projects will not interfere with our interpretation of our study results. If tracts meet all criteria, we will flag it as 1 for tracts with NMTC projects and 0 for tracts without an NMTC project:

Code

# Find count of NMTC projects after 2010
# Remove all tracts that do not have SVI flag counts for 2010
# Remove all tracts that do not have SVI flag counts for 2020
# Remove all tracts that had an NMTC project before 2010
svi_divisional_nmtc <- 
  left_join(svi_divisional_nmtc_eligible, nmtc_awards_post2010, join_by("GEOID_2010_trt" == "GEOID10")) %>%
  mutate(post10_nmtc_project_cnt = if_else(is.na(post10_nmtc_project_cnt), 0, post10_nmtc_project_cnt)) %>%
  mutate(post10_nmtc_dollars = if_else(is.na(post10_nmtc_dollars), 0, post10_nmtc_dollars))%>%
  mutate(post10_nmtc_dollars_formatted = if_else(is.na(post10_nmtc_dollars_formatted), "$0", post10_nmtc_dollars_formatted)) %>%
  mutate(nmtc_flag = if_else(post10_nmtc_project_cnt > 0, 1, 0)) %>% 
  filter(!is.na(F_TOTAL_10)) %>% 
  filter(!is.na(F_TOTAL_20)) %>% 
  filter(pre10_nmtc_project_cnt < 1)

svi_divisional_nmtc %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID_2010_trt	FIPS_st	FIPS_county	FIPS_tract	state	state_name	county	region_number	region	division_number	division	E_TOTPOP_10	E_HU_10	E_HH_10	E_POV150_10	ET_POVSTATUS_10	EP_POV150_10	EPL_POV150_10	F_POV150_10	E_UNEMP_10	ET_EMPSTATUS_10	EP_UNEMP_10	EPL_UNEMP_10	F_UNEMP_10	E_HBURD_OWN_10	ET_HOUSINGCOST_OWN_10	EP_HBURD_OWN_10	EPL_HBURD_OWN_10	F_HBURD_OWN_10	E_HBURD_RENT_10	ET_HOUSINGCOST_RENT_10	EP_HBURD_RENT_10	EPL_HBURD_RENT_10	F_HBURD_RENT_10	E_HBURD_10	ET_HOUSINGCOST_10	EP_HBURD_10	EPL_HBURD_10	F_HBURD_10	E_NOHSDP_10	ET_EDSTATUS_10	EP_NOHSDP_10	EPL_NOHSDP_10	F_NOHSDP_10	E_UNINSUR_12	ET_INSURSTATUS_12	EP_UNINSUR_12	EPL_UNINSUR_12	F_UNINSUR_12	E_AGE65_10	EP_AGE65_10	EPL_AGE65_10	F_AGE65_10	E_AGE17_10	EP_AGE17_10	EPL_AGE17_10	F_AGE17_10	E_DISABL_12	ET_DISABLSTATUS_12	EP_DISABL_12	EPL_DISABL_12	F_DISABL_12	E_SNGPNT_10	ET_FAMILIES_10	EP_SNGPNT_10	EPL_SNGPNT_10	F_SNGPNT_10	E_LIMENG_10	ET_POPAGE5UP_10	EP_LIMENG_10	EPL_LIMENG_10	F_LIMENG_10	E_MINRTY_10	ET_POPETHRACE_10	EP_MINRTY_10	EPL_MINRTY_10	F_MINRTY_10	E_STRHU_10	E_MUNIT_10	EP_MUNIT_10	EPL_MUNIT_10	F_MUNIT_10	E_MOBILE_10	EP_MOBILE_10	EPL_MOBILE_10	E_CROWD_10	ET_OCCUPANTS_10	EP_CROWD_10	EPL_CROWD_10	F_CROWD_10	E_NOVEH_10	ET_KNOWNVEH_10	EP_NOVEH_10	EPL_NOVEH_10	F_NOVEH_10	ET_HHTYPE_10	EPL_GROUPQ_10	SPL_THEME1_10	RPL_THEME1_10	F_THEME1_10	SPL_THEME2_10	RPL_THEME2_10	F_THEME2_10	SPL_THEME3_10	RPL_THEME3_10	F_THEME3_10	SPL_THEME4_10	RPL_THEME4_10	F_THEME4_10	SPL_THEMES_10	RPL_THEMES_10	F_TOTAL_10	E_TOTPOP_20	E_HU_20	E_HH_20	E_POV150_20	ET_POVSTATUS_20	EP_POV150_20	EPL_POV150_20	F_POV150_20	E_UNEMP_20	ET_EMPSTATUS_20	EP_UNEMP_20	EPL_UNEMP_20	F_UNEMP_20	E_HBURD_OWN_20	ET_HOUSINGCOST_OWN_20	EP_HBURD_OWN_20	EPL_HBURD_OWN_20	F_HBURD_OWN_20	E_HBURD_RENT_20	ET_HOUSINGCOST_RENT_20	EP_HBURD_RENT_20	EPL_HBURD_RENT_20	F_HBURD_RENT_20	E_HBURD_20	ET_HOUSINGCOST_20	EP_HBURD_20	EPL_HBURD_20	F_HBURD_20	E_NOHSDP_20	ET_EDSTATUS_20	EP_NOHSDP_20	EPL_NOHSDP_20	F_NOHSDP_20	E_UNINSUR_20	ET_INSURSTATUS_20	EP_UNINSUR_20	EPL_UNINSUR_20	F_UNINSUR_20	E_AGE65_20	EP_AGE65_20	EPL_AGE65_20	E_AGE17_20	EP_AGE17_20	EPL_AGE17_20	F_AGE17_20	E_DISABL_20	ET_DISABLSTATUS_20	EP_DISABL_20	EPL_DISABL_20	F_DISABL_20	E_SNGPNT_20	ET_FAMILIES_20	EP_SNGPNT_20	EPL_SNGPNT_20	F_SNGPNT_20	E_LIMENG_20	ET_POPAGE5UP_20	EP_LIMENG_20	EPL_LIMENG_20	F_LIMENG_20	E_MINRTY_20	ET_POPETHRACE_20	EP_MINRTY_20	EPL_MINRTY_20	F_MINRTY_20	E_STRHU_20	E_MUNIT_20	EP_MUNIT_20	EPL_MUNIT_20	F_MUNIT_20	E_MOBILE_20	EP_MOBILE_20	EPL_MOBILE_20	F_MOBILE_20	E_CROWD_20	ET_OCCUPANTS_20	EP_CROWD_20	EPL_CROWD_20	F_CROWD_20	E_NOVEH_20	ET_KNOWNVEH_20	EP_NOVEH_20	EPL_NOVEH_20	F_NOVEH_20	E_GROUPQ_20	ET_HHTYPE_20	EP_GROUPQ_20	EPL_GROUPQ_20	SPL_THEME1_20	RPL_THEME1_20	F_THEME1_20	SPL_THEME2_20	RPL_THEME2_20	F_THEME2_20	SPL_THEME3_20	RPL_THEME3_20	F_THEME3_20	SPL_THEME4_20	RPL_THEME4_20	F_THEME4_20	SPL_THEMES_20	RPL_THEMES_20	F_TOTAL_20	nmtc_eligibility	pre10_nmtc_dollars_formatted	post10_nmtc_dollars_formatted
34001000100	34	001	000100	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2907	1088	983	1127	2907	38.76849	0.8482	1	144	1433	10.048849	0.7544	1	280	435	64.36782	0.9529	1	204	548	37.22628	0.2998	0	484	983	49.23703	0.7813	1	468	1759	26.60603	0.8634	1	532	2543	20.92017	0.8978	1	250	8.599931	0.1777	0	944	32.47334	0.94170	1	186	1851	10.04862	0.2706	0	266	678	39.233038	0.8981	1	177	2611	6.779012	0.7778	1	1928	2907	66.32267	0.7743	1	1088	113	10.386029	0.6229	0	9	0.8272059	0.7223	80	983	8.138352	0.8657	1	265	983	26.95829	0.7354	0	2907	0.3512	4.1451	0.8935	5	3.06590	0.7944	3	0.7743	0.7667	1	3.2975	0.8414	1	11.28280	0.8862	10	2157	941	784	1182	2157	54.79833	0.9571	1	242	1058	22.873346	0.9922	1	215	342	62.86550	0.9780	1	316	442	71.49321	0.9481	1	531	784	67.72959	0.9893	1	396	1274	31.08320	0.9497	1	266	2157	12.331943	0.9041	1	185	8.576727	0.09430	552	25.59110	0.8128	1	297	1605	18.504673	0.74880	0	83	510	16.27451	0.6090	0	251	2020	12.425743	0.87100	1	1852	2157	85.85999	0.8476	1	941	118	12.5398512	0.6385	0	0	0.00000	0.3216	0	67	784	8.545918	0.8657	1	212	784	27.04082	0.7502	1	0	2157	0.0000000	0.1517	4.7924	0.9850	5	3.13590	0.8217	2	0.8476	0.8400	1	2.7277	0.6085	2	11.50360	0.9104	10	Yes	$0	$0
34001000200	34	001	000200	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3189	2217	1473	519	3189	16.27469	0.4806	0	109	1558	6.996149	0.5179	0	573	955	60.00000	0.9323	1	199	518	38.41699	0.3261	0	772	1473	52.41005	0.8418	1	405	2579	15.70376	0.6491	0	484	3547	13.64533	0.7154	0	847	26.560050	0.9629	1	436	13.67200	0.08181	0	608	3005	20.23295	0.8466	1	42	857	4.900817	0.1204	0	422	3072	13.736979	0.8799	1	1792	3189	56.19316	0.7390	0	2217	901	40.640505	0.8693	1	0	0.0000000	0.3251	48	1473	3.258656	0.7064	0	250	1473	16.97217	0.6444	0	3189	0.3512	3.2048	0.6963	1	2.89161	0.7231	3	0.7390	0.7317	0	2.8964	0.6887	1	9.73181	0.7340	5	3510	2046	1353	1021	3510	29.08832	0.7682	1	121	1852	6.533477	0.6717	0	343	696	49.28161	0.9273	1	416	657	63.31811	0.8696	1	759	1353	56.09756	0.9321	1	553	2338	23.65269	0.8871	1	354	3510	10.085470	0.8530	1	643	18.319088	0.60310	1002	28.54701	0.9055	1	450	2508	17.942584	0.72330	0	237	786	30.15267	0.8539	1	534	3375	15.822222	0.90620	1	2534	3510	72.19373	0.7818	1	2046	906	44.2815249	0.8690	1	0	0.00000	0.3216	0	119	1353	8.795270	0.8711	1	324	1353	23.94678	0.7255	0	0	3510	0.0000000	0.1517	4.1121	0.9003	4	3.99200	0.9781	3	0.7818	0.7747	1	2.9389	0.7011	2	11.82480	0.9310	10	Yes	$0	$0
34001000300	34	001	000300	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3997	1823	1357	1401	3968	35.30746	0.8164	1	382	2238	17.068811	0.9376	1	176	329	53.49544	0.8855	1	604	1028	58.75486	0.7947	1	780	1357	57.47973	0.9165	1	920	2677	34.36683	0.9346	1	1351	4149	32.56206	0.9811	1	314	7.855892	0.1437	0	937	23.44258	0.55900	0	319	3054	10.44532	0.3000	0	187	782	23.913044	0.7498	0	1080	3671	29.419777	0.9742	1	3357	3997	83.98799	0.8419	1	1823	363	19.912233	0.7535	1	0	0.0000000	0.3251	150	1357	11.053795	0.9136	1	651	1357	47.97347	0.8585	1	3997	0.3512	4.5862	0.9691	5	2.72670	0.6360	1	0.8419	0.8336	1	3.2019	0.8054	3	11.35670	0.8920	10	3801	1640	1226	1857	3801	48.85556	0.9333	1	226	1800	12.555556	0.9267	1	111	280	39.64286	0.8339	1	608	946	64.27061	0.8842	1	719	1226	58.64600	0.9528	1	650	2275	28.57143	0.9337	1	1027	3801	27.019206	0.9914	1	380	9.997369	0.14040	1223	32.17574	0.9607	1	219	2578	8.494957	0.15680	0	268	909	29.48295	0.8456	1	940	3400	27.647059	0.97280	1	3318	3801	87.29282	0.8579	1	1640	262	15.9756098	0.6917	0	0	0.00000	0.3216	0	124	1226	10.114192	0.8955	1	477	1226	38.90701	0.8258	1	0	3801	0.0000000	0.1517	4.7379	0.9829	5	3.07630	0.8013	3	0.8579	0.8501	1	2.8863	0.6781	2	11.55840	0.9150	11	Yes	$0	$0
34001000500	34	001	000500	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3483	1241	1027	1938	3483	55.64169	0.9533	1	124	1630	7.607362	0.5830	0	227	446	50.89686	0.8549	1	478	581	82.27194	0.9799	1	705	1027	68.64654	0.9863	1	733	2077	35.29129	0.9396	1	727	3258	22.31430	0.9149	1	377	10.824002	0.3081	0	1055	30.28998	0.90140	1	268	2401	11.16202	0.3549	0	209	763	27.391874	0.7940	1	911	3077	29.606760	0.9746	1	3036	3483	87.16624	0.8550	1	1241	52	4.190169	0.4505	0	4	0.3223207	0.6567	113	1027	11.002921	0.9128	1	422	1027	41.09056	0.8250	1	3483	0.3512	4.3771	0.9379	4	3.33300	0.8766	3	0.8550	0.8467	1	3.1962	0.8026	2	11.76130	0.9229	10	3385	1185	945	1682	3364	50.00000	0.9391	1	72	1577	4.565631	0.4586	0	185	468	39.52991	0.8332	1	362	477	75.89099	0.9703	1	547	945	57.88360	0.9477	1	592	1983	29.85376	0.9422	1	738	3385	21.802068	0.9817	1	240	7.090103	0.05988	1129	33.35303	0.9689	1	135	2256	5.984043	0.04817	0	110	717	15.34170	0.5822	0	721	3076	23.439532	0.95690	1	3029	3385	89.48301	0.8727	1	1185	9	0.7594937	0.2382	0	0	0.00000	0.3216	0	103	945	10.899471	0.9072	1	263	945	27.83069	0.7560	1	0	3385	0.0000000	0.1517	4.2693	0.9283	4	2.61605	0.5709	2	0.8727	0.8648	1	2.3747	0.4357	2	10.13275	0.7921	9	Yes	$0	$0
34001001100	34	001	001100	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2204	1204	1204	1185	2204	53.76588	0.9457	1	219	927	23.624596	0.9830	1	97	172	56.39535	0.9094	1	462	1032	44.76744	0.4746	0	559	1204	46.42857	0.7197	0	346	1440	24.02778	0.8306	1	469	1942	24.15036	0.9360	1	363	16.470054	0.7020	0	578	26.22505	0.74410	0	442	1558	28.36970	0.9675	1	247	396	62.373737	0.9898	1	104	2051	5.070697	0.7260	0	2118	2204	96.09800	0.9204	1	1204	570	47.342193	0.8858	1	0	0.0000000	0.3251	14	1204	1.162791	0.4877	0	817	1204	67.85714	0.9413	1	2204	0.3512	4.4150	0.9451	4	4.12940	0.9805	2	0.9204	0.9114	1	2.9911	0.7243	2	12.45590	0.9597	9	1950	1267	1096	1131	1950	58.00000	0.9678	1	66	706	9.348442	0.8395	1	42	101	41.58416	0.8612	1	309	995	31.05528	0.1959	0	351	1096	32.02555	0.4782	0	510	1379	36.98332	0.9763	1	155	1950	7.948718	0.7660	1	392	20.102564	0.69880	447	22.92308	0.6712	0	570	1503	37.924152	0.99200	1	143	374	38.23529	0.9167	1	109	1841	5.920695	0.74640	0	1909	1950	97.89744	0.9529	1	1267	479	37.8058406	0.8464	1	0	0.00000	0.3216	0	33	1096	3.010949	0.6446	0	743	1096	67.79197	0.9414	1	0	1950	0.0000000	0.1517	4.0278	0.8848	4	4.02510	0.9798	2	0.9529	0.9442	1	2.9057	0.6869	2	11.91150	0.9365	9	Yes	$0	$0
34001001300	34	001	001300	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2153	1026	857	695	2153	32.28054	0.7840	1	266	1112	23.920863	0.9840	1	168	432	38.88889	0.6425	0	271	425	63.76471	0.8714	1	439	857	51.22520	0.8184	1	210	1471	14.27600	0.5989	0	463	2215	20.90293	0.8974	1	334	15.513237	0.6436	0	539	25.03484	0.66990	0	222	1687	13.15945	0.4984	0	265	608	43.585526	0.9249	1	92	1905	4.829396	0.7187	0	1993	2153	92.56851	0.8890	1	1026	147	14.327485	0.6885	0	0	0.0000000	0.3251	20	857	2.333722	0.6326	0	142	857	16.56943	0.6382	0	2153	0.3512	4.0827	0.8798	4	3.45550	0.9039	1	0.8890	0.8804	1	2.6356	0.5687	0	11.06280	0.8673	6	1632	917	770	591	1632	36.21324	0.8455	1	203	854	23.770492	0.9928	1	164	291	56.35739	0.9604	1	364	479	75.99165	0.9710	1	528	770	68.57143	0.9914	1	150	1056	14.20455	0.7232	0	97	1632	5.943627	0.6352	0	301	18.443628	0.60940	271	16.60539	0.2292	0	314	1361	23.071271	0.88960	1	148	410	36.09756	0.9025	1	0	1585	0.000000	0.06953	0	1512	1632	92.64706	0.8931	1	917	246	26.8266085	0.7912	1	16	1.74482	0.7855	1	0	770	0.000000	0.1194	0	219	770	28.44156	0.7606	1	14	1632	0.8578431	0.6722	4.1881	0.9131	3	2.70023	0.6211	2	0.8931	0.8850	1	3.1289	0.7740	3	10.91033	0.8638	9	Yes	$0	$0

Code

# Find count of NMTC projects after 2010
# Remove all tracts that do not have SVI flag counts for 2010
# Remove all tracts that do not have SVI flag counts for 2020
# Remove all tracts that had an NMTC project before 2010
svi_national_nmtc <- 
  left_join(svi_national_nmtc_eligible, nmtc_awards_post2010, join_by("GEOID_2010_trt" == "GEOID10")) %>%
  mutate(post10_nmtc_project_cnt = if_else(is.na(post10_nmtc_project_cnt), 0, post10_nmtc_project_cnt)) %>%
  mutate(post10_nmtc_dollars = if_else(is.na(post10_nmtc_dollars), 0, post10_nmtc_dollars))%>%
  mutate(post10_nmtc_dollars_formatted = if_else(is.na(post10_nmtc_dollars_formatted), "$0", post10_nmtc_dollars_formatted)) %>%
  mutate(nmtc_flag = if_else(post10_nmtc_project_cnt > 0, 1, 0)) %>% 
  filter(!is.na(F_TOTAL_10)) %>% 
  filter(!is.na(F_TOTAL_20)) %>% 
  filter(pre10_nmtc_project_cnt < 1)

svi_national_nmtc %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID_2010_trt	FIPS_st	FIPS_county	FIPS_tract	state	state_name	county	region_number	region	division_number	division	E_TOTPOP_10	E_HU_10	E_HH_10	E_POV150_10	ET_POVSTATUS_10	EP_POV150_10	EPL_POV150_10	F_POV150_10	E_UNEMP_10	ET_EMPSTATUS_10	EP_UNEMP_10	EPL_UNEMP_10	F_UNEMP_10	E_HBURD_OWN_10	ET_HOUSINGCOST_OWN_10	EP_HBURD_OWN_10	EPL_HBURD_OWN_10	E_HBURD_RENT_10	ET_HOUSINGCOST_RENT_10	EP_HBURD_RENT_10	EPL_HBURD_RENT_10	E_HBURD_10	ET_HOUSINGCOST_10	EP_HBURD_10	EPL_HBURD_10	E_NOHSDP_10	ET_EDSTATUS_10	EP_NOHSDP_10	EPL_NOHSDP_10	F_NOHSDP_10	E_UNINSUR_12	ET_INSURSTATUS_12	EP_UNINSUR_12	EPL_UNINSUR_12	E_AGE65_10	EP_AGE65_10	EPL_AGE65_10	E_AGE17_10	EP_AGE17_10	EPL_AGE17_10	F_AGE17_10	E_DISABL_12	ET_DISABLSTATUS_12	EP_DISABL_12	EPL_DISABL_12	F_DISABL_12	E_SNGPNT_10	ET_FAMILIES_10	EP_SNGPNT_10	EPL_SNGPNT_10	F_SNGPNT_10	E_LIMENG_10	ET_POPAGE5UP_10	EP_LIMENG_10	EPL_LIMENG_10	E_MINRTY_10	ET_POPETHRACE_10	EP_MINRTY_10	EPL_MINRTY_10	F_MINRTY_10	E_STRHU_10	E_MUNIT_10	EP_MUNIT_10	EPL_MUNIT_10	E_MOBILE_10	EP_MOBILE_10	EPL_MOBILE_10	F_MOBILE_10	E_CROWD_10	ET_OCCUPANTS_10	EP_CROWD_10	EPL_CROWD_10	F_CROWD_10	E_NOVEH_10	ET_KNOWNVEH_10	EP_NOVEH_10	EPL_NOVEH_10	F_NOVEH_10	E_GROUPQ_10	ET_HHTYPE_10	EP_GROUPQ_10	EPL_GROUPQ_10	F_GROUPQ_10	SPL_THEME1_10	RPL_THEME1_10	F_THEME1_10	SPL_THEME2_10	RPL_THEME2_10	F_THEME2_10	SPL_THEME3_10	RPL_THEME3_10	F_THEME3_10	SPL_THEME4_10	RPL_THEME4_10	F_THEME4_10	SPL_THEMES_10	RPL_THEMES_10	F_TOTAL_10	E_TOTPOP_20	E_HU_20	E_HH_20	E_POV150_20	ET_POVSTATUS_20	EP_POV150_20	EPL_POV150_20	F_POV150_20	E_UNEMP_20	ET_EMPSTATUS_20	EP_UNEMP_20	EPL_UNEMP_20	F_UNEMP_20	E_HBURD_OWN_20	ET_HOUSINGCOST_OWN_20	EP_HBURD_OWN_20	EPL_HBURD_OWN_20	F_HBURD_OWN_20	E_HBURD_RENT_20	ET_HOUSINGCOST_RENT_20	EP_HBURD_RENT_20	EPL_HBURD_RENT_20	F_HBURD_RENT_20	E_HBURD_20	ET_HOUSINGCOST_20	EP_HBURD_20	EPL_HBURD_20	F_HBURD_20	E_NOHSDP_20	ET_EDSTATUS_20	EP_NOHSDP_20	EPL_NOHSDP_20	F_NOHSDP_20	E_UNINSUR_20	ET_INSURSTATUS_20	EP_UNINSUR_20	EPL_UNINSUR_20	F_UNINSUR_20	E_AGE65_20	EP_AGE65_20	EPL_AGE65_20	F_AGE65_20	E_AGE17_20	EP_AGE17_20	EPL_AGE17_20	F_AGE17_20	E_DISABL_20	ET_DISABLSTATUS_20	EP_DISABL_20	EPL_DISABL_20	F_DISABL_20	E_SNGPNT_20	ET_FAMILIES_20	EP_SNGPNT_20	EPL_SNGPNT_20	F_SNGPNT_20	E_LIMENG_20	ET_POPAGE5UP_20	EP_LIMENG_20	EPL_LIMENG_20	E_MINRTY_20	ET_POPETHRACE_20	EP_MINRTY_20	EPL_MINRTY_20	F_MINRTY_20	E_STRHU_20	E_MUNIT_20	EP_MUNIT_20	EPL_MUNIT_20	E_MOBILE_20	EP_MOBILE_20	EPL_MOBILE_20	F_MOBILE_20	E_CROWD_20	ET_OCCUPANTS_20	EP_CROWD_20	EPL_CROWD_20	F_CROWD_20	E_NOVEH_20	ET_KNOWNVEH_20	EP_NOVEH_20	EPL_NOVEH_20	E_GROUPQ_20	ET_HHTYPE_20	EP_GROUPQ_20	EPL_GROUPQ_20	F_GROUPQ_20	SPL_THEME1_20	RPL_THEME1_20	F_THEME1_20	SPL_THEME2_20	RPL_THEME2_20	F_THEME2_20	SPL_THEME3_20	RPL_THEME3_20	F_THEME3_20	SPL_THEME4_20	RPL_THEME4_20	F_THEME4_20	SPL_THEMES_20	RPL_THEMES_20	F_TOTAL_20	nmtc_eligibility	pre10_nmtc_dollars_formatted	post10_nmtc_project_cnt	post10_nmtc_dollars	post10_nmtc_dollars_formatted	nmtc_flag
01001020200	01	001	020200	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	2020	816	730	495	1992	24.84940	0.5954	0	68	834	8.153477	0.57540	0	49	439	11.16173	0.02067	105	291	36.08247	0.30190	154	730	21.09589	0.09312	339	1265	26.79842	0.8392	1	313	2012	15.55666	0.6000	204	10.09901	0.3419	597	29.55446	0.8192	1	359	1515	23.69637	0.8791	1	132	456	28.947368	0.8351	1	15	1890	0.7936508	0.40130	1243	2020	61.53465	0.7781	1	816	0	0.0000000	0.1224	34	4.1666667	0.6664	0	13	730	1.780822	0.5406	0	115	730	15.753425	0.8382	1	0	2020	0.0000	0.3640	0	2.70312	0.5665	1	3.27660	0.8614	3	0.7781	0.7709	1	2.5316	0.5047	1	9.28942	0.6832	6	1757	720	573	384	1511	25.41363	0.6427	0	29	717	4.044630	0.4132	0	33	392	8.418367	0.03542	0	116	181	64.08840	0.9086	1	149	573	26.00349	0.40410	0	139	1313	10.58644	0.5601	0	91	1533	5.936073	0.4343	0	284	16.163916	0.5169	0	325	18.49744	0.2851	0	164	1208.000	13.57616	0.4127	0	42	359.0000	11.699164	0.3998	0	0	1651	0.0000000	0.09479	1116	1757.000	63.51736	0.7591	1	720	3	0.4166667	0.2470	5	0.6944444	0.5106	0	9	573	1.5706806	0.4688	0	57	573.000	9.947644	0.7317	212	1757	12.0660216	0.9549	1	2.45440	0.4888	0	1.70929	0.1025	0	0.7591	0.7527	1	2.9130	0.6862	1	7.83579	0.4802	2	Yes	$0	0	0	$0	0
01001020700	01	001	020700	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	2664	1254	1139	710	2664	26.65165	0.6328	0	29	1310	2.213741	0.05255	0	134	710	18.87324	0.13890	187	429	43.58974	0.47090	321	1139	28.18262	0.28130	396	1852	21.38229	0.7478	0	345	2878	11.98749	0.4459	389	14.60210	0.6417	599	22.48499	0.4007	0	510	2168	23.52399	0.8752	1	228	712	32.022472	0.8712	1	0	2480	0.0000000	0.09298	694	2664	26.05105	0.5138	0	1254	8	0.6379585	0.2931	460	36.6826156	0.9714	1	0	1139	0.000000	0.1238	0	125	1139	10.974539	0.7477	0	0	2664	0.0000	0.3640	0	2.16035	0.4069	0	2.88178	0.6997	2	0.5138	0.5090	0	2.5000	0.4882	1	8.05593	0.5185	3	3562	1313	1248	1370	3528	38.83220	0.8512	1	128	1562	8.194622	0.7935	1	168	844	19.905213	0.44510	0	237	404	58.66337	0.8359	1	405	1248	32.45192	0.60420	0	396	2211	17.91045	0.7857	1	444	3547	12.517620	0.7758	1	355	9.966311	0.1800	0	954	26.78271	0.7923	1	629	2593.000	24.25762	0.8730	1	171	797.0000	21.455458	0.7186	0	0	3211	0.0000000	0.09479	1009	3562.000	28.32678	0.4668	0	1313	14	1.0662605	0.3165	443	33.7395278	0.9663	1	73	1248	5.8493590	0.8211	1	17	1248.000	1.362180	0.1554	112	3562	3.1443010	0.8514	1	3.81040	0.8569	4	2.65869	0.5847	2	0.4668	0.4629	0	3.1107	0.7714	3	10.04659	0.7851	9	Yes	$0	0	0	$0	0
01001021100	01	001	021100	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	3298	1502	1323	860	3298	26.07641	0.6211	0	297	1605	18.504673	0.94340	1	250	1016	24.60630	0.32070	74	307	24.10423	0.11920	324	1323	24.48980	0.17380	710	2231	31.82429	0.8976	1	654	3565	18.34502	0.7018	411	12.46210	0.5001	738	22.37720	0.3934	0	936	2861	32.71583	0.9807	1	138	825	16.727273	0.5715	0	9	3155	0.2852615	0.25010	1979	3298	60.00606	0.7703	1	1502	14	0.9320905	0.3234	659	43.8748336	0.9849	1	44	1323	3.325775	0.7062	0	137	1323	10.355253	0.7313	0	0	3298	0.0000	0.3640	0	3.33770	0.7351	2	2.69580	0.6028	1	0.7703	0.7631	1	3.1098	0.7827	1	9.91360	0.7557	5	3499	1825	1462	1760	3499	50.30009	0.9396	1	42	966	4.347826	0.4539	0	426	1274	33.437991	0.85200	1	52	188	27.65957	0.1824	0	478	1462	32.69494	0.61110	0	422	2488	16.96141	0.7638	1	497	3499	14.204058	0.8246	1	853	24.378394	0.8688	1	808	23.09231	0.5829	0	908	2691.100	33.74084	0.9808	1	179	811.6985	22.052524	0.7323	0	8	3248	0.2463054	0.26220	1986	3498.713	56.76373	0.7175	0	1825	29	1.5890411	0.3551	576	31.5616438	0.9594	1	88	1462	6.0191518	0.8269	1	148	1461.993	10.123166	0.7364	38	3499	1.0860246	0.7013	0	3.59300	0.8073	3	3.42700	0.9156	2	0.7175	0.7114	0	3.5791	0.9216	2	11.31660	0.9150	7	Yes	$0	0	0	$0	0
01003010200	01	003	010200	AL	Alabama	Baldwin County	3	South Region	6	East South Central Division	2612	1220	1074	338	2605	12.97505	0.2907	0	44	1193	3.688181	0.14720	0	172	928	18.53448	0.13090	31	146	21.23288	0.09299	203	1074	18.90130	0.05657	455	1872	24.30556	0.8016	1	456	2730	16.70330	0.6445	401	15.35222	0.6847	563	21.55436	0.3406	0	410	2038	20.11776	0.7755	1	64	779	8.215661	0.2181	0	0	2510	0.0000000	0.09298	329	2612	12.59571	0.3113	0	1220	38	3.1147541	0.4648	385	31.5573770	0.9545	1	20	1074	1.862197	0.5509	0	43	1074	4.003724	0.4088	0	0	2612	0.0000	0.3640	0	1.94057	0.3398	1	2.11188	0.2802	1	0.3113	0.3084	0	2.7430	0.6129	1	7.10675	0.3771	3	2928	1312	1176	884	2928	30.19126	0.7334	0	29	1459	1.987663	0.1356	0	71	830	8.554217	0.03726	0	134	346	38.72832	0.3964	0	205	1176	17.43197	0.12010	0	294	2052	14.32749	0.6940	0	219	2925	7.487179	0.5423	0	556	18.989071	0.6705	0	699	23.87295	0.6339	0	489	2226.455	21.96317	0.8122	1	191	783.8820	24.365914	0.7799	1	0	2710	0.0000000	0.09479	398	2927.519	13.59513	0.2511	0	1312	13	0.9908537	0.3111	400	30.4878049	0.9557	1	6	1176	0.5102041	0.2590	0	81	1176.202	6.886570	0.6115	7	2928	0.2390710	0.4961	0	2.22540	0.4183	0	2.99129	0.7634	2	0.2511	0.2490	0	2.6334	0.5496	1	8.10119	0.5207	3	Yes	$0	1	408000	$408,000	1
01003010500	01	003	010500	AL	Alabama	Baldwin County	3	South Region	6	East South Central Division	4230	1779	1425	498	3443	14.46413	0.3337	0	166	1625	10.215385	0.71790	0	151	1069	14.12535	0.04638	196	356	55.05618	0.73830	347	1425	24.35088	0.17010	707	2945	24.00679	0.7967	1	528	4001	13.19670	0.5005	619	14.63357	0.6436	790	18.67612	0.1937	0	536	3096	17.31266	0.6572	0	165	920	17.934783	0.6102	0	20	4021	0.4973887	0.32320	754	4230	17.82506	0.4023	0	1779	97	5.4525014	0.5525	8	0.4496908	0.4600	0	63	1425	4.421053	0.7762	1	90	1425	6.315790	0.5691	0	787	4230	18.6052	0.9649	1	2.51890	0.5121	1	2.42790	0.4539	0	0.4023	0.3986	0	3.3227	0.8628	2	8.67180	0.6054	3	5877	1975	1836	820	5244	15.63692	0.3902	0	90	2583	3.484321	0.3361	0	159	1345	11.821561	0.10530	0	139	491	28.30957	0.1924	0	298	1836	16.23094	0.09053	0	570	4248	13.41808	0.6669	0	353	5247	6.727654	0.4924	0	1109	18.870172	0.6645	0	1144	19.46571	0.3411	0	717	4102.545	17.47696	0.6332	0	103	1286.1180	8.008596	0.2341	0	0	5639	0.0000000	0.09479	868	5877.481	14.76823	0.2709	0	1975	26	1.3164557	0.3359	45	2.2784810	0.6271	0	9	1836	0.4901961	0.2540	0	116	1835.798	6.318779	0.5811	633	5877	10.7708014	0.9507	1	1.97613	0.3410	0	1.96769	0.1961	0	0.2709	0.2686	0	2.7488	0.6077	1	6.96352	0.3406	1	Yes	$0	0	0	$0	0
01003010600	01	003	010600	AL	Alabama	Baldwin County	3	South Region	6	East South Central Division	3724	1440	1147	1973	3724	52.98067	0.9342	1	142	1439	9.867964	0.69680	0	235	688	34.15698	0.62950	187	459	40.74074	0.40290	422	1147	36.79163	0.55150	497	1876	26.49254	0.8354	1	511	3661	13.95794	0.5334	246	6.60580	0.1481	1256	33.72718	0.9305	1	496	2522	19.66693	0.7587	1	274	838	32.696897	0.8779	1	32	3479	0.9198045	0.42810	2606	3724	69.97852	0.8184	1	1440	21	1.4583333	0.3683	321	22.2916667	0.9036	1	97	1147	8.456844	0.8956	1	167	1147	14.559721	0.8209	1	0	3724	0.0000	0.3640	0	3.55130	0.7859	2	3.14330	0.8145	3	0.8184	0.8108	1	3.3524	0.8725	3	10.86540	0.8550	9	4115	1534	1268	1676	3997	41.93145	0.8814	1	294	1809	16.252073	0.9674	1	341	814	41.891892	0.94320	1	204	454	44.93392	0.5438	0	545	1268	42.98107	0.83620	1	624	2425	25.73196	0.9002	1	994	4115	24.155529	0.9602	1	642	15.601458	0.4841	0	1126	27.36331	0.8175	1	568	2989.000	19.00301	0.7045	0	212	715.0000	29.650350	0.8592	1	56	3825	1.4640523	0.53120	2715	4115.000	65.97813	0.7732	1	1534	0	0.0000000	0.1079	529	34.4850065	0.9685	1	101	1268	7.9652997	0.8795	1	89	1268.000	7.018927	0.6184	17	4115	0.4131227	0.5707	0	4.54540	0.9754	5	3.39650	0.9081	2	0.7732	0.7667	1	3.1450	0.7858	2	11.86010	0.9520	10	Yes	$0	1	8000000	$8,000,000	1

Code

# See all the states in data set with eligible tracts
svi_national_nmtc %>% 
  select(state) %>% 
  arrange(state) %>% 
  unique() %>% 
  mutate(n = row_number()) %>% 
  kbl() %>% kable_styling() %>% scroll_box(width = "100%")

state	n
AK	1
AL	2
AR	3
AZ	4
CA	5
CO	6
CT	7
DC	8
DE	9
FL	10
GA	11
HI	12
IA	13
ID	14
IL	15
IN	16
KS	17
KY	18
LA	19
MA	20
MD	21
ME	22
MI	23
MN	24
MO	25
MS	26
MT	27
NC	28
ND	29
NE	30
NH	31
NJ	32
NM	33
NV	34
NY	35
OH	36
OK	37
OR	38
PA	39
RI	40
SC	41
SD	42
TN	43
TX	44
UT	45
VA	46
VT	47
WA	48
WI	49
WV	50
WY	51

Code

# See all the states in data set with projects
svi_national_nmtc %>% 
  filter(nmtc_flag == 1) %>% 
  select(state) %>% 
  arrange(state) %>% 
  unique() %>% 
  mutate(n = row_number()) %>% 
  kbl() %>% kable_styling() %>% scroll_box(width = "100%")

state	n
AK	1
AL	2
AR	3
AZ	4
CA	5
CO	6
CT	7
DC	8
DE	9
FL	10
GA	11
HI	12
IA	13
ID	14
IL	15
IN	16
KS	17
KY	18
LA	19
MA	20
MD	21
ME	22
MI	23
MN	24
MO	25
MS	26
MT	27
NC	28
ND	29
NE	30
NH	31
NJ	32
NM	33
NV	34
NY	35
OH	36
OK	37
OR	38
PA	39
RI	40
SC	41
SD	42
TN	43
TX	44
UT	45
VA	46
VT	47
WA	48
WI	49
WV	50
WY	51

View final number of rows in data set:

National

Code

# See number of rows
svi_national_nmtc %>% nrow()

[1] 29068

Code

# View number of tracts with NMTC projects
svi_national_nmtc %>% filter(nmtc_flag == 1) %>% nrow()

[1] 2054

Code

# View number of tracts without NMTC projects
svi_national_nmtc %>% filter(nmtc_flag == 0) %>% nrow()

[1] 27014

Code

# See distribution of flags for SVI themes in top quarter in 2010
table(svi_national_nmtc$F_TOTAL_10)


   0    1    2    3    4    5    6    7    8    9   10   11   12   13   14   15 
 324 1177 2071 2679 2922 2975 2906 2849 2831 2776 2557 1782  904  264   45    6

Code

# Average number of flags in 2010
mean(svi_national_nmtc$F_TOTAL_10)

[1] 6.367896

Code

# See distribution of flags for SVI themes in top quarter in 2020
table(svi_national_nmtc$F_TOTAL_20)


   0    1    2    3    4    5    6    7    8    9   10   11   12   13   14   15 
 329 1070 1930 2620 3074 3195 3304 3243 3045 2745 2188 1415  674  203   32    1

Code

# Average number of flags in 2020
mean(svi_national_nmtc$F_TOTAL_20)

[1] 6.236618

Divisional

Code

# See number of rows
svi_divisional_nmtc %>% nrow()

[1] 3704

Code

# View number of tracts with NMTC projects
svi_divisional_nmtc %>% filter(nmtc_flag == 1) %>% nrow()

[1] 174

Code

# View number of tracts without NMTC projects
svi_divisional_nmtc %>% filter(nmtc_flag == 0) %>% nrow()

[1] 3530

Code

# See distribution of flags for SVI themes in top quarter in 2010
table(svi_divisional_nmtc$F_TOTAL_10)


  0   1   2   3   4   5   6   7   8   9  10  11  12  13  14  15 
 40 148 241 350 321 323 340 346 361 331 336 282 183  90  11   1

Code

# Average number of flags in 2010
mean(svi_divisional_nmtc$F_TOTAL_10)

[1] 6.723812

Code

# See distribution of flags for SVI themes in top quarter in 2020
table(svi_divisional_nmtc$F_TOTAL_20)


  0   1   2   3   4   5   6   7   8   9  10  11  12  13  14  15 
 42 119 217 349 396 348 349 346 371 356 296 255 156  86  17   1

Code

# Average number of flags in 2020
mean(svi_divisional_nmtc$F_TOTAL_20)

[1] 6.646868

County-Level SVI NMTC Data

Recall that we have data on counties in our data set:

Code

colnames(svi_divisional_nmtc) %>% head(11)

 [1] "GEOID_2010_trt"  "FIPS_st"         "FIPS_county"     "FIPS_tract"     
 [5] "state"           "state_name"      "county"          "region_number"  
 [9] "region"          "division_number" "division"

Therefore we can summarize our project counts up to the county-level for easier visualizations with the following function NOTE: Remember to add all functions to project_data_steps.R :

Code

summarize_county_nmtc <- function(df) {
  # Find count of new NMTC projects after 2010 by county
  county_nmtc_project_cnt <- aggregate(df$post10_nmtc_project_cnt,
                                       by=list(State=df$state,
                                               County=df$county,
                                               Division=df$division), 
                                       FUN=sum) %>% 
                                      arrange(State, County) %>%
                                      rename("post10_nmtc_project_cnt" = "x")
  
  # Find count of census tracts in each county
  county_nmtc_tracts <- aggregate(df$GEOID_2010_trt,
                                  by=list(State=df$state,
                                          County=df$county,
                                          Division=df$division), 
                                  FUN=length) %>% 
                                  mutate(tract_cnt = x) %>% 
                                  select (-x)
  
  # Find sum of NMTC project dollars in each county
  county_nmtc_dollars <- aggregate(df$post10_nmtc_dollars,
                                   by=list(State=df$state,
                                           County=df$county,
                                           Division=df$division), 
                                   FUN=sum) %>% 
                                  arrange(State, County) %>%
                                  rename("post10_nmtc_project_dollars" = "x")
  
  # Create character column with NMTC dollars formatted as currency
  county_nmtc_dollars$post10_nmtc_dollars_formatted <-
    scales::dollar_format()(county_nmtc_dollars$post10_nmtc_project_dollars)

  # Join project counts and census tract counts datasets
  county_nmtc0 <- left_join(county_nmtc_project_cnt, county_nmtc_tracts,
                            join_by("State" == "State",
                                    "County" == "County",
                                    "Division" == "Division"))

  # Add dollar amounts
  county_nmtc <- left_join(county_nmtc0, county_nmtc_dollars,
                         join_by("State" == "State",
                                 "County" == "County",
                                 "Division" == "Division"))
  
  # Output data
  return(county_nmtc)
}

Code

svi_national_nmtc_county_sum <- summarize_county_nmtc(svi_national_nmtc)

svi_national_nmtc_county_sum %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

State	County	Division	post10_nmtc_project_cnt	tract_cnt	post10_nmtc_project_dollars	post10_nmtc_dollars_formatted
AK	Aleutians East Borough	Pacific Division	1	1	15762500	$15,762,500
AK	Aleutians West Census Area	Pacific Division	0	1	0	$0
AK	Anchorage Municipality	Pacific Division	1	13	9800000	$9,800,000
AK	Bethel Census Area	Pacific Division	0	1	0	$0
AK	Fairbanks North Star Borough	Pacific Division	0	4	0	$0
AK	Hoonah-Angoon Census Area	Pacific Division	0	1	0	$0

Code

svi_divisional_nmtc_county_sum <- summarize_county_nmtc(svi_divisional_nmtc)
svi_divisional_nmtc_county_sum %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

State	County	Division	post10_nmtc_project_cnt	tract_cnt	post10_nmtc_project_dollars	post10_nmtc_dollars_formatted
NJ	Atlantic County	Middle Atlantic Division	0	29	0	$0
NJ	Bergen County	Middle Atlantic Division	1	30	10000000	$10,000,000
NJ	Burlington County	Middle Atlantic Division	0	20	0	$0
NJ	Camden County	Middle Atlantic Division	5	47	79664200	$79,664,200
NJ	Cape May County	Middle Atlantic Division	0	12	0	$0
NJ	Cumberland County	Middle Atlantic Division	2	21	33187593	$33,187,593

We can then utilize our flag_summarize function from Lab 03 to find our county-level SVI flag calculations:

Code

# Create data frame of NMTC eligible tracts 2010 nationally
svi_national_nmtc10 <- svi_national_nmtc %>% select(GEOID_2010_trt, FIPS_st, FIPS_county, 
    state, state_name, county, region_number, region, division_number, 
    division, F_TOTAL_10, E_TOTPOP_10) %>% rename("F_TOTAL" = "F_TOTAL_10")

# Count national-level SVI flags for 2010, create unified fips column
svi_2010_national_county_flags_nmtc <- flag_summarize(svi_national_nmtc10, "E_TOTPOP_10") %>% unite("fips_county_st", FIPS_st:FIPS_county, remove = FALSE, sep="")

# Add suffix to flag columns 2010
colnames(svi_2010_national_county_flags_nmtc)[11:15] <- paste0(colnames(svi_2010_national_county_flags_nmtc)[11:15], 10)

# Create data frame of NMTC eligible tracts 2020 nationally
svi_national_nmtc20 <- svi_national_nmtc %>% select(GEOID_2010_trt, FIPS_st, FIPS_county, 
    state, state_name, county, region_number, region, division_number, 
    division, F_TOTAL_20, E_TOTPOP_20) %>% rename("F_TOTAL" = "F_TOTAL_20")

# Count national-level SVI flags for 2020, create unified fips column
svi_2020_national_county_flags_nmtc <- flag_summarize(svi_national_nmtc20, "E_TOTPOP_20") %>% unite("fips_county_st", FIPS_st:FIPS_county, remove = FALSE, sep="")

# Identify needed columns for 2020, add suffix
colnames(svi_2020_national_county_flags_nmtc)[11:15] <- paste0(colnames(svi_2020_national_county_flags_nmtc)[11:15], "20")

# Filter to needed columns for 2020 to avoid duplicate column column names
svi_2020_national_county_flags_join_nmtc <- svi_2020_national_county_flags_nmtc %>% ungroup() %>% select("fips_county_st", all_of(colnames(svi_2020_national_county_flags_nmtc)[11:15]))
 
# Join 2010 and 2020 data
svi_national_county_flags_nmtc <- left_join(svi_2010_national_county_flags_nmtc, svi_2020_national_county_flags_join_nmtc, join_by("fips_county_st" == "fips_county_st")) 

svi_national_county_flags_nmtc %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

fips_county_st	FIPS_st	FIPS_county	state	state_name	county	region_number	region	division_number	division	flag_count10	pop10	flag_by_pop10	flag_count_quantile10	flag_pop_quantile10	flag_count20	pop20	flag_by_pop20	flag_count_quantile20	flag_pop_quantile20
01001	01	001	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	14	7982	0.0017539	0.6	0.8	18	8818	0.0020413	0.6	1.0
01003	01	003	AL	Alabama	Baldwin County	3	South Region	6	East South Central Division	34	38458	0.0008841	0.8	0.4	34	46255	0.0007351	0.8	0.2
01005	01	005	AL	Alabama	Barbour County	3	South Region	6	East South Central Division	43	21287	0.0020200	0.8	1.0	44	18811	0.0023391	0.8	1.0
01007	01	007	AL	Alabama	Bibb County	3	South Region	6	East South Central Division	11	17570	0.0006261	0.4	0.2	16	17663	0.0009058	0.6	0.4
01009	01	009	AL	Alabama	Blount County	3	South Region	6	East South Central Division	12	16995	0.0007061	0.4	0.2	8	16546	0.0004835	0.4	0.2
01011	01	011	AL	Alabama	Bullock County	3	South Region	6	East South Central Division	21	10923	0.0019225	0.6	1.0	18	10173	0.0017694	0.6	0.8

Join flags with NMTC county project summary data:

Code

svi_national_county_nmtc <- left_join(svi_national_nmtc_county_sum,
                                      svi_national_county_flags_nmtc,
                                    join_by("State" == "state", "County" == "county",
                                            "Division" == "division"))

svi_national_county_nmtc$post10_nmtc_project_cnt[is.na(svi_national_county_nmtc$post10_nmtc_project_cnt)] <- 0

svi_national_county_nmtc$county_name <- paste0(svi_national_county_nmtc$County, ", ", svi_national_county_nmtc$State)

svi_national_county_nmtc %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

State	County	Division	post10_nmtc_project_cnt	tract_cnt	post10_nmtc_project_dollars	post10_nmtc_dollars_formatted	fips_county_st	FIPS_st	FIPS_county	state_name	region_number	region	division_number	flag_count10	pop10	flag_by_pop10	flag_count_quantile10	flag_pop_quantile10	flag_count20	pop20	flag_by_pop20	flag_count_quantile20	flag_pop_quantile20	county_name
AK	Aleutians East Borough	Pacific Division	1	1	15762500	$15,762,500	02013	02	013	Alaska	4	West Region	9	8	3703	0.0021604	0.4	1.0	5	3389	0.0014754	0.2	0.8	Aleutians East Borough, AK
AK	Aleutians West Census Area	Pacific Division	0	1	0	$0	02016	02	016	Alaska	4	West Region	9	6	1774	0.0033822	0.2	1.0	6	950	0.0063158	0.2	1.0	Aleutians West Census Area, AK
AK	Anchorage Municipality	Pacific Division	1	13	9800000	$9,800,000	02020	02	020	Alaska	4	West Region	9	72	64432	0.0011175	1.0	0.4	87	69679	0.0012486	1.0	0.6	Anchorage Municipality, AK
AK	Bethel Census Area	Pacific Division	0	1	0	$0	02050	02	050	Alaska	4	West Region	9	8	1386	0.0057720	0.4	1.0	10	1404	0.0071225	0.4	1.0	Bethel Census Area, AK
AK	Fairbanks North Star Borough	Pacific Division	0	4	0	$0	02090	02	090	Alaska	4	West Region	9	13	17281	0.0007523	0.4	0.2	17	20094	0.0008460	0.6	0.4	Fairbanks North Star Borough, AK
AK	Hoonah-Angoon Census Area	Pacific Division	0	1	0	$0	02105	02	105	Alaska	4	West Region	9	4	1888	0.0021186	0.2	1.0	5	2073	0.0024120	0.2	1.0	Hoonah-Angoon Census Area, AK

Code

# Create data frame of NMTC eligible tracts 2020 nationally
svi_divisional_nmtc10 <- svi_divisional_nmtc %>% select(GEOID_2010_trt, FIPS_st, FIPS_county, 
    state, state_name, county, region_number, region, division_number, 
    division, F_TOTAL_10, E_TOTPOP_10) %>% rename("F_TOTAL" = "F_TOTAL_10")

# Count divisional-level SVI flags for 2010, create unified fips column
svi_2010_divisional_county_flags_nmtc <- flag_summarize(svi_divisional_nmtc10, "E_TOTPOP_10") %>% unite("fips_county_st", FIPS_st:FIPS_county, remove = FALSE, sep="")

# Add suffix to flag columns 2010
colnames(svi_2010_divisional_county_flags_nmtc)[11:15] <- paste0(colnames(svi_2010_divisional_county_flags_nmtc)[11:15], "10")

# Create data frame of NMTC eligible tracts 2020 nationally
svi_divisional_nmtc20 <- svi_divisional_nmtc %>% select(GEOID_2010_trt, FIPS_st, FIPS_county, 
    state, state_name, county, region_number, region, division_number, 
    division, F_TOTAL_20, E_TOTPOP_20) %>% rename("F_TOTAL" = "F_TOTAL_20")

# Count divisional-level SVI flags for 2020, create unified fips column
svi_2020_divisional_county_flags_nmtc <- flag_summarize(svi_divisional_nmtc20, "E_TOTPOP_20") %>% unite("fips_county_st", FIPS_st:FIPS_county, remove = FALSE, sep="")

# Identify needed columns for 2020
colnames(svi_2020_divisional_county_flags_nmtc)[11:15] <- paste0(colnames(svi_2020_divisional_county_flags_nmtc)[11:15], "20")

# Filter to needed columns for 2020 to avoid duplicate column column names
svi_2020_divisional_county_flags_join_nmtc <- svi_2020_divisional_county_flags_nmtc %>% ungroup() %>% select("fips_county_st", all_of(colnames(svi_2020_divisional_county_flags_nmtc)[11:15]))
 
# Join 2010 and 2020 data
svi_divisional_county_flags_nmtc <- left_join(svi_2010_divisional_county_flags_nmtc, svi_2020_divisional_county_flags_join_nmtc, join_by("fips_county_st" == "fips_county_st")) 

svi_divisional_county_flags_nmtc %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

fips_county_st	FIPS_st	FIPS_county	state	state_name	county	region_number	region	division_number	division	flag_count10	pop10	flag_by_pop10	flag_count_quantile10	flag_pop_quantile10	flag_count20	pop20	flag_by_pop20	flag_count_quantile20	flag_pop_quantile20
34001	34	001	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	202	111752	0.0018076	1.0	1.0	220	108778	0.0020225	1.0	1.0
34003	34	003	NJ	New Jersey	Bergen County	1	Northeast Region	2	Middle Atlantic Division	146	143973	0.0010141	1.0	0.4	165	154365	0.0010689	1.0	0.4
34005	34	005	NJ	New Jersey	Burlington County	1	Northeast Region	2	Middle Atlantic Division	84	62519	0.0013436	0.8	0.6	86	61250	0.0014041	0.8	0.6
34007	34	007	NJ	New Jersey	Camden County	1	Northeast Region	2	Middle Atlantic Division	332	183630	0.0018080	1.0	1.0	315	180659	0.0017436	1.0	0.8
34009	34	009	NJ	New Jersey	Cape May County	1	Northeast Region	2	Middle Atlantic Division	59	39917	0.0014781	0.8	0.8	47	39348	0.0011945	0.6	0.6
34011	34	011	NJ	New Jersey	Cumberland County	1	Northeast Region	2	Middle Atlantic Division	138	101151	0.0013643	0.8	0.6	135	97989	0.0013777	0.8	0.6

Join flags with NMTC county project summary data for division:

Code

svi_divisional_county_nmtc <- left_join(svi_divisional_nmtc_county_sum, 
                                        svi_divisional_county_flags_nmtc,
                                    join_by("State" == "state", "County" == "county",
                                            "Division" == "division"))

svi_divisional_county_nmtc$post10_nmtc_project_cnt[is.na(svi_divisional_county_nmtc $post10_nmtc_project_cnt)] <- 0

svi_divisional_county_nmtc$county_name <- paste0(svi_divisional_county_nmtc$County, ", ", svi_divisional_county_nmtc$State)

svi_divisional_county_nmtc %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

State	County	Division	post10_nmtc_project_cnt	tract_cnt	post10_nmtc_project_dollars	post10_nmtc_dollars_formatted	fips_county_st	FIPS_st	FIPS_county	state_name	region_number	region	division_number	flag_count10	pop10	flag_by_pop10	flag_count_quantile10	flag_pop_quantile10	flag_count20	pop20	flag_by_pop20	flag_count_quantile20	flag_pop_quantile20	county_name
NJ	Atlantic County	Middle Atlantic Division	0	29	0	$0	34001	34	001	New Jersey	1	Northeast Region	2	202	111752	0.0018076	1.0	1.0	220	108778	0.0020225	1.0	1.0	Atlantic County, NJ
NJ	Bergen County	Middle Atlantic Division	1	30	10000000	$10,000,000	34003	34	003	New Jersey	1	Northeast Region	2	146	143973	0.0010141	1.0	0.4	165	154365	0.0010689	1.0	0.4	Bergen County, NJ
NJ	Burlington County	Middle Atlantic Division	0	20	0	$0	34005	34	005	New Jersey	1	Northeast Region	2	84	62519	0.0013436	0.8	0.6	86	61250	0.0014041	0.8	0.6	Burlington County, NJ
NJ	Camden County	Middle Atlantic Division	5	47	79664200	$79,664,200	34007	34	007	New Jersey	1	Northeast Region	2	332	183630	0.0018080	1.0	1.0	315	180659	0.0017436	1.0	0.8	Camden County, NJ
NJ	Cape May County	Middle Atlantic Division	0	12	0	$0	34009	34	009	New Jersey	1	Northeast Region	2	59	39917	0.0014781	0.8	0.8	47	39348	0.0011945	0.6	0.6	Cape May County, NJ
NJ	Cumberland County	Middle Atlantic Division	2	21	33187593	$33,187,593	34011	34	011	New Jersey	1	Northeast Region	2	138	101151	0.0013643	0.8	0.6	135	97989	0.0013777	0.8	0.6	Cumberland County, NJ

LIHTC Data Wrangling

Now that we have our NMTC data wrangled, we need to repeat these steps for our LIHTC data:

Code

# View column names
colnames(lihtc_eligible)

 [1] "state"    "county"   "stcnty"   "tract"    "fips"     "splittr" 
 [7] "qct_id"   "old_cnty" "metro"    "areapop"  "cbsa"     "cbsasub" 
[13] "amgi2000" "amgi60pc" "pop100"   "p015001"  "p016001"  "p087001" 
[19] "p087002"  "hhinc01"  "hhinc02"  "hhinc03"  "hhinc04"  "hhinc05" 
[25] "hhinc06"  "hhinc07"  "hhinc08"  "hhinc09"  "hhinc10"  "hhinc11" 
[31] "hhinc12"  "hhinc13"  "hhinc14"  "hhinc15"  "hhinc16"  "hhinc17" 
[37] "hhinc18"  "hhinc19"  "hhinc20"  "hhinc21"  "hhinc22"  "hhinc23" 
[43] "hhinc24"  "hhinc25"  "hhinc26"  "hhinc27"  "hhinc28"  "hhinc29" 
[49] "hhinc30"  "hhinc31"  "hhinc32"  "hhinc33"  "hhinc34"  "hhinc35" 
[55] "hhinc36"  "pctinc"   "povrate"  "qct_2010"

First we need to process our LIHTC eligibility data set to identify all census tracts eligible for the program:

Code

lihtc_eligible_flag <- lihtc_eligible %>% 
  select("fips", "state", "county", "stcnty", "tract", "metro", "cbsa", "qct_2010") %>% 
  rename("GEOID10" = "fips") %>% 
  mutate(lihtc_eligibility = if_else(qct_2010 == 1, "Yes", "No")) %>% 
  filter(tolower(lihtc_eligibility) == "yes") %>% 
  select(GEOID10, lihtc_eligibility)

lihtc_eligible_flag %>% head()

# A tibble: 6 × 2
  GEOID10     lihtc_eligibility
  <chr>       <chr>            
1 01003010600 Yes              
2 01005950200 Yes              
3 01005950300 Yes              
4 01005950400 Yes              
5 01005950600 Yes              
6 01005950700 Yes

Now we need to process our LIHTC projects data set to filter out the null values in our data set (we can identify these because we should not have any data for years in the 8000s or later (at least not yet 😉)). We also need to filter to only keep projects in 2010 or before:

Code

lihtc_projects10 <- lihtc_projects %>% 
  filter(yr_alloc < 8000) %>% 
  filter(yr_alloc <= 2010) %>% 
  count(fips2010) %>% 
  rename("pre10_lihtc_project_cnt" = "n")

lihtc_projects10 %>% head()

     fips2010 pre10_lihtc_project_cnt
1 01001020300                       2
2 01001020500                       5
3 01001021100                       1
4 01003010200                       1
5 01003010600                       1
6 01003010703                       1

Next, we can find the number of dollars in tax credits each tract received during this time:

Code

lihtc_dollars10 <- lihtc_projects %>% 
  filter(yr_alloc < 8000) %>% 
  filter(yr_alloc <= 2010) %>%
  select(fips2010, allocamt)

lihtc_dollars10$allocamt[is.na(lihtc_dollars10$allocamt)] <- 0

lihtc_dollars10 <- lihtc_dollars10 %>% 
  group_by(fips2010) %>% 
  summarise(pre10_lihtc_project_dollars = sum(allocamt, na.rm = TRUE))

lihtc_dollars10 %>% head()

# A tibble: 6 × 2
  fips2010    pre10_lihtc_project_dollars
  <chr>                             <dbl>
1 01001020300                      216593
2 01001020500                     2250459
3 01001021100                       53109
4 01003010200                           0
5 01003010600                      376889
6 01003010703                      717113

We can then join this to our projects data set:

Code

lihtc_projects10 <- left_join(lihtc_projects10, lihtc_dollars10, join_by(fips2010 == fips2010))

lihtc_projects10 %>% head()

     fips2010 pre10_lihtc_project_cnt pre10_lihtc_project_dollars
1 01001020300                       2                      216593
2 01001020500                       5                     2250459
3 01001021100                       1                       53109
4 01003010200                       1                           0
5 01003010600                       1                      376889
6 01003010703                       1                      717113

Now we need to create a second data set of projects after 2010 and before 2021 (2011-2020):

Code

colnames(lihtc_projects)

 [1] "hud_id"            "project"           "proj_add"         
 [4] "proj_cty"          "proj_st"           "proj_zip"         
 [7] "state_id"          "latitude"          "longitude"        
[10] "place1990"         "place2000"         "place2010"        
[13] "fips1990"          "fips2000"          "fips2010"         
[16] "st2010"            "cnty2010"          "scattered_site_cd"
[19] "resyndication_cd"  "allocamt"          "n_units"          
[22] "li_units"          "n_0br"             "n_1br"            
[25] "n_2br"             "n_3br"             "n_4br"            
[28] "inc_ceil"          "low_ceil"          "ceilunit"         
[31] "yr_pis"            "yr_alloc"          "non_prof"         
[34] "basis"             "bond"              "mff_ra"           
[37] "fmha_514"          "fmha_515"          "fmha_538"         
[40] "home"              "home_amt"          "tcap"             
[43] "tcap_amt"          "cdbg"              "cdbg_amt"         
[46] "htf"               "htf_amt"           "fha"              
[49] "hopevi"            "hpvi_amt"          "tcep"             
[52] "tcep_amt"          "rad"               "qozf"             
[55] "qozf_amt"          "rentassist"        "trgt_pop"         
[58] "trgt_fam"          "trgt_eld"          "trgt_dis"         
[61] "trgt_hml"          "trgt_other"        "trgt_spc"         
[64] "type"              "credit"            "n_unitsr"         
[67] "li_unitr"          "metro"             "dda"              
[70] "qct"               "nonprog"           "nlm_reason"       
[73] "nlm_spc"           "datanote"          "record_stat"

Code

lihtc_projects20 <- lihtc_projects %>% 
  filter(yr_alloc < 8000) %>% 
  filter(yr_alloc > 2010) %>% 
  filter(yr_alloc < 2021) %>% 
  count(fips2010) %>% 
  rename("post10_lihtc_project_cnt" = "n")

lihtc_projects20 %>% head()

     fips2010 post10_lihtc_project_cnt
1 01003010500                        1
2 01003011403                        1
3 01003011601                        1
4 01005950900                        1
5 01009050102                        1
6 01017954600                        2

Once again, we need to find the number of dollars in tax credits each tract received during this time:

Code

lihtc_dollars20 <- lihtc_projects %>% 
  filter(yr_alloc < 8000) %>% 
  filter(yr_alloc > 2010) %>% 
  filter(yr_alloc < 2021) %>% 
  select(fips2010, allocamt)

lihtc_dollars20$allocamt[is.na(lihtc_dollars20$allocamt)] <- 0

lihtc_dollars20 <- lihtc_dollars20 %>% 
  group_by(fips2010) %>% 
  summarise(post10_lihtc_project_dollars = sum(allocamt, na.rm = TRUE))

lihtc_dollars20 %>% head()

# A tibble: 6 × 2
  fips2010    post10_lihtc_project_dollars
  <chr>                              <dbl>
1 01003010500                       481325
2 01003011403                       828342
3 01003011601                       887856
4 01005950900                       400758
5 01009050102                       463000
6 01017954600                       950192

Code

lihtc_projects20 <- left_join(lihtc_projects20, lihtc_dollars20, join_by(fips2010 == fips2010))

lihtc_projects20 %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

fips2010	post10_lihtc_project_cnt	post10_lihtc_project_dollars
01003010500	1	481325
01003011403	1	828342
01003011601	1	887856
01005950900	1	400758
01009050102	1	463000
01017954600	2	950192

Next, we need to join with our SVI divisional and national data:

Code

svi_divisional_lihtc10 <- left_join(svi_divisional, lihtc_projects10, join_by("GEOID_2010_trt" == "fips2010"))

svi_divisional_lihtc10 %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID_2010_trt	FIPS_st	FIPS_county	FIPS_tract	state	state_name	county	region_number	region	division_number	division	E_TOTPOP_10	E_HU_10	E_HH_10	E_POV150_10	ET_POVSTATUS_10	EP_POV150_10	EPL_POV150_10	F_POV150_10	E_UNEMP_10	ET_EMPSTATUS_10	EP_UNEMP_10	EPL_UNEMP_10	F_UNEMP_10	E_HBURD_OWN_10	ET_HOUSINGCOST_OWN_10	EP_HBURD_OWN_10	EPL_HBURD_OWN_10	F_HBURD_OWN_10	E_HBURD_RENT_10	ET_HOUSINGCOST_RENT_10	EP_HBURD_RENT_10	EPL_HBURD_RENT_10	F_HBURD_RENT_10	E_HBURD_10	ET_HOUSINGCOST_10	EP_HBURD_10	EPL_HBURD_10	F_HBURD_10	E_NOHSDP_10	ET_EDSTATUS_10	EP_NOHSDP_10	EPL_NOHSDP_10	F_NOHSDP_10	E_UNINSUR_12	ET_INSURSTATUS_12	EP_UNINSUR_12	EPL_UNINSUR_12	F_UNINSUR_12	E_AGE65_10	EP_AGE65_10	EPL_AGE65_10	F_AGE65_10	E_AGE17_10	EP_AGE17_10	EPL_AGE17_10	F_AGE17_10	E_DISABL_12	ET_DISABLSTATUS_12	EP_DISABL_12	EPL_DISABL_12	F_DISABL_12	E_SNGPNT_10	ET_FAMILIES_10	EP_SNGPNT_10	EPL_SNGPNT_10	F_SNGPNT_10	E_LIMENG_10	ET_POPAGE5UP_10	EP_LIMENG_10	EPL_LIMENG_10	F_LIMENG_10	E_MINRTY_10	ET_POPETHRACE_10	EP_MINRTY_10	EPL_MINRTY_10	F_MINRTY_10	E_STRHU_10	E_MUNIT_10	EP_MUNIT_10	EPL_MUNIT_10	F_MUNIT_10	E_MOBILE_10	EP_MOBILE_10	EPL_MOBILE_10	E_CROWD_10	ET_OCCUPANTS_10	EP_CROWD_10	EPL_CROWD_10	F_CROWD_10	E_NOVEH_10	ET_KNOWNVEH_10	EP_NOVEH_10	EPL_NOVEH_10	F_NOVEH_10	E_GROUPQ_10	ET_HHTYPE_10	EP_GROUPQ_10	EPL_GROUPQ_10	F_GROUPQ_10	SPL_THEME1_10	RPL_THEME1_10	F_THEME1_10	SPL_THEME2_10	RPL_THEME2_10	F_THEME2_10	SPL_THEME3_10	RPL_THEME3_10	F_THEME3_10	SPL_THEME4_10	RPL_THEME4_10	F_THEME4_10	SPL_THEMES_10	RPL_THEMES_10	F_TOTAL_10	E_TOTPOP_20	E_HU_20	E_HH_20	E_POV150_20	ET_POVSTATUS_20	EP_POV150_20	EPL_POV150_20	F_POV150_20	E_UNEMP_20	ET_EMPSTATUS_20	EP_UNEMP_20	EPL_UNEMP_20	F_UNEMP_20	E_HBURD_OWN_20	ET_HOUSINGCOST_OWN_20	EP_HBURD_OWN_20	EPL_HBURD_OWN_20	F_HBURD_OWN_20	E_HBURD_RENT_20	ET_HOUSINGCOST_RENT_20	EP_HBURD_RENT_20	EPL_HBURD_RENT_20	F_HBURD_RENT_20	E_HBURD_20	ET_HOUSINGCOST_20	EP_HBURD_20	EPL_HBURD_20	F_HBURD_20	E_NOHSDP_20	ET_EDSTATUS_20	EP_NOHSDP_20	EPL_NOHSDP_20	F_NOHSDP_20	E_UNINSUR_20	ET_INSURSTATUS_20	EP_UNINSUR_20	EPL_UNINSUR_20	F_UNINSUR_20	E_AGE65_20	EP_AGE65_20	EPL_AGE65_20	E_AGE17_20	EP_AGE17_20	EPL_AGE17_20	F_AGE17_20	E_DISABL_20	ET_DISABLSTATUS_20	EP_DISABL_20	EPL_DISABL_20	F_DISABL_20	E_SNGPNT_20	ET_FAMILIES_20	EP_SNGPNT_20	EPL_SNGPNT_20	F_SNGPNT_20	E_LIMENG_20	ET_POPAGE5UP_20	EP_LIMENG_20	EPL_LIMENG_20	F_LIMENG_20	E_MINRTY_20	ET_POPETHRACE_20	EP_MINRTY_20	EPL_MINRTY_20	F_MINRTY_20	E_STRHU_20	E_MUNIT_20	EP_MUNIT_20	EPL_MUNIT_20	F_MUNIT_20	E_MOBILE_20	EP_MOBILE_20	EPL_MOBILE_20	E_CROWD_20	ET_OCCUPANTS_20	EP_CROWD_20	EPL_CROWD_20	F_CROWD_20	E_NOVEH_20	ET_KNOWNVEH_20	EP_NOVEH_20	EPL_NOVEH_20	F_NOVEH_20	E_GROUPQ_20	ET_HHTYPE_20	EP_GROUPQ_20	EPL_GROUPQ_20	SPL_THEME1_20	RPL_THEME1_20	F_THEME1_20	SPL_THEME2_20	RPL_THEME2_20	F_THEME2_20	SPL_THEME3_20	RPL_THEME3_20	F_THEME3_20	SPL_THEME4_20	RPL_THEME4_20	F_THEME4_20	SPL_THEMES_20	RPL_THEMES_20	F_TOTAL_20	pre10_lihtc_project_cnt	pre10_lihtc_project_dollars
34001000100	34	001	000100	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2907	1088	983	1127	2907	38.76849	0.8482	1	144	1433	10.048849	0.7544	1	280	435	64.36782	0.9529	1	204	548	37.22628	0.2998	0	484	983	49.23703	0.7813	1	468	1759	26.60603	0.8634	1	532	2543	20.92017	0.8978	1	250	8.599931	0.1777	0	944	32.47334	0.94170	1	186	1851	10.04862	0.2706	0	266	678	39.233038	0.8981	1	177	2611	6.779012	0.7778	1	1928	2907	66.32267	0.7743	1	1088	113	10.386029	0.6229	0	9	0.8272059	0.7223	80	983	8.138352	0.8657	1	265	983	26.95829	0.7354	0	0	2907	0.000000	0.3512	0	4.1451	0.8935	5	3.06590	0.7944	3	0.7743	0.7667	1	3.2975	0.8414	1	11.28280	0.8862	10	2157	941	784	1182	2157	54.79833	0.9571	1	242	1058	22.873346	0.9922	1	215	342	62.86550	0.9780	1	316	442	71.49321	0.9481	1	531	784	67.72959	0.9893	1	396	1274	31.08320	0.9497	1	266	2157	12.331943	0.9041	1	185	8.576727	0.09430	552	25.59110	0.8128	1	297	1605	18.504673	0.74880	0	83	510	16.27451	0.6090	0	251	2020	12.425743	0.8710	1	1852	2157	85.85999	0.8476	1	941	118	12.5398512	0.6385	0	0	0.0000000	0.3216	67	784	8.545918	0.8657	1	212	784	27.04082	0.7502	1	0	2157	0.0000000	0.1517	4.7924	0.9850	5	3.13590	0.8217	2	0.8476	0.8400	1	2.7277	0.6085	2	11.50360	0.9104	10	NA	NA
34001000200	34	001	000200	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3189	2217	1473	519	3189	16.27469	0.4806	0	109	1558	6.996149	0.5179	0	573	955	60.00000	0.9323	1	199	518	38.41699	0.3261	0	772	1473	52.41005	0.8418	1	405	2579	15.70376	0.6491	0	484	3547	13.64533	0.7154	0	847	26.560050	0.9629	1	436	13.67200	0.08181	0	608	3005	20.23295	0.8466	1	42	857	4.900817	0.1204	0	422	3072	13.736979	0.8799	1	1792	3189	56.19316	0.7390	0	2217	901	40.640505	0.8693	1	0	0.0000000	0.3251	48	1473	3.258656	0.7064	0	250	1473	16.97217	0.6444	0	0	3189	0.000000	0.3512	0	3.2048	0.6963	1	2.89161	0.7231	3	0.7390	0.7317	0	2.8964	0.6887	1	9.73181	0.7340	5	3510	2046	1353	1021	3510	29.08832	0.7682	1	121	1852	6.533477	0.6717	0	343	696	49.28161	0.9273	1	416	657	63.31811	0.8696	1	759	1353	56.09756	0.9321	1	553	2338	23.65269	0.8871	1	354	3510	10.085470	0.8530	1	643	18.319088	0.60310	1002	28.54701	0.9055	1	450	2508	17.942584	0.72330	0	237	786	30.15267	0.8539	1	534	3375	15.822222	0.9062	1	2534	3510	72.19373	0.7818	1	2046	906	44.2815249	0.8690	1	0	0.0000000	0.3216	119	1353	8.795270	0.8711	1	324	1353	23.94678	0.7255	0	0	3510	0.0000000	0.1517	4.1121	0.9003	4	3.99200	0.9781	3	0.7818	0.7747	1	2.9389	0.7011	2	11.82480	0.9310	10	NA	NA
34001000300	34	001	000300	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3997	1823	1357	1401	3968	35.30746	0.8164	1	382	2238	17.068811	0.9376	1	176	329	53.49544	0.8855	1	604	1028	58.75486	0.7947	1	780	1357	57.47973	0.9165	1	920	2677	34.36683	0.9346	1	1351	4149	32.56206	0.9811	1	314	7.855892	0.1437	0	937	23.44258	0.55900	0	319	3054	10.44532	0.3000	0	187	782	23.913044	0.7498	0	1080	3671	29.419777	0.9742	1	3357	3997	83.98799	0.8419	1	1823	363	19.912233	0.7535	1	0	0.0000000	0.3251	150	1357	11.053795	0.9136	1	651	1357	47.97347	0.8585	1	0	3997	0.000000	0.3512	0	4.5862	0.9691	5	2.72670	0.6360	1	0.8419	0.8336	1	3.2019	0.8054	3	11.35670	0.8920	10	3801	1640	1226	1857	3801	48.85556	0.9333	1	226	1800	12.555556	0.9267	1	111	280	39.64286	0.8339	1	608	946	64.27061	0.8842	1	719	1226	58.64600	0.9528	1	650	2275	28.57143	0.9337	1	1027	3801	27.019206	0.9914	1	380	9.997369	0.14040	1223	32.17574	0.9607	1	219	2578	8.494957	0.15680	0	268	909	29.48295	0.8456	1	940	3400	27.647059	0.9728	1	3318	3801	87.29282	0.8579	1	1640	262	15.9756098	0.6917	0	0	0.0000000	0.3216	124	1226	10.114192	0.8955	1	477	1226	38.90701	0.8258	1	0	3801	0.0000000	0.1517	4.7379	0.9829	5	3.07630	0.8013	3	0.8579	0.8501	1	2.8863	0.6781	2	11.55840	0.9150	11	NA	NA
34001000400	34	001	000400	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2902	2683	1401	1172	2902	40.38594	0.8615	1	190	1389	13.678906	0.8811	1	364	707	51.48515	0.8627	1	507	694	73.05476	0.9503	1	871	1401	62.16988	0.9572	1	481	1981	24.28067	0.8339	1	674	3204	21.03620	0.8998	1	434	14.955203	0.6083	0	596	20.53756	0.33980	0	426	2607	16.34062	0.6886	0	111	652	17.024540	0.6204	0	215	2736	7.858187	0.8008	1	1792	2902	61.75052	0.7584	1	2683	2049	76.369735	0.9401	1	0	0.0000000	0.3251	69	1401	4.925053	0.7847	1	511	1401	36.47395	0.7992	1	72	2902	2.481048	0.8114	1	4.4335	0.9468	5	3.05790	0.7908	1	0.7584	0.7510	1	3.6605	0.9391	4	11.91030	0.9339	11	3178	2264	1390	1508	3176	47.48111	0.9246	1	172	1804	9.534368	0.8460	1	205	468	43.80342	0.8858	1	622	922	67.46204	0.9192	1	827	1390	59.49640	0.9587	1	364	2076	17.53372	0.8013	1	476	3178	14.977974	0.9390	1	483	15.198238	0.41220	539	16.96035	0.2484	0	319	2639	12.087912	0.38790	0	101	565	17.87611	0.6539	0	583	3022	19.291860	0.9349	1	2186	3178	68.78540	0.7658	1	2264	1609	71.0689046	0.9266	1	15	0.6625442	0.7078	226	1390	16.258993	0.9567	1	599	1390	43.09353	0.8474	1	20	3178	0.6293266	0.6292	4.4696	0.9558	5	2.63730	0.5864	1	0.7658	0.7588	1	4.0677	0.9762	3	11.94040	0.9387	10	NA	NA
34001000500	34	001	000500	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3483	1241	1027	1938	3483	55.64169	0.9533	1	124	1630	7.607362	0.5830	0	227	446	50.89686	0.8549	1	478	581	82.27194	0.9799	1	705	1027	68.64654	0.9863	1	733	2077	35.29129	0.9396	1	727	3258	22.31430	0.9149	1	377	10.824002	0.3081	0	1055	30.28998	0.90140	1	268	2401	11.16202	0.3549	0	209	763	27.391874	0.7940	1	911	3077	29.606760	0.9746	1	3036	3483	87.16624	0.8550	1	1241	52	4.190169	0.4505	0	4	0.3223207	0.6567	113	1027	11.002921	0.9128	1	422	1027	41.09056	0.8250	1	0	3483	0.000000	0.3512	0	4.3771	0.9379	4	3.33300	0.8766	3	0.8550	0.8467	1	3.1962	0.8026	2	11.76130	0.9229	10	3385	1185	945	1682	3364	50.00000	0.9391	1	72	1577	4.565631	0.4586	0	185	468	39.52991	0.8332	1	362	477	75.89099	0.9703	1	547	945	57.88360	0.9477	1	592	1983	29.85376	0.9422	1	738	3385	21.802068	0.9817	1	240	7.090103	0.05988	1129	33.35303	0.9689	1	135	2256	5.984043	0.04817	0	110	717	15.34170	0.5822	0	721	3076	23.439532	0.9569	1	3029	3385	89.48301	0.8727	1	1185	9	0.7594937	0.2382	0	0	0.0000000	0.3216	103	945	10.899471	0.9072	1	263	945	27.83069	0.7560	1	0	3385	0.0000000	0.1517	4.2693	0.9283	4	2.61605	0.5709	2	0.8727	0.8648	1	2.3747	0.4357	2	10.13275	0.7921	9	NA	NA
34001001100	34	001	001100	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2204	1204	1204	1185	2204	53.76588	0.9457	1	219	927	23.624596	0.9830	1	97	172	56.39535	0.9094	1	462	1032	44.76744	0.4746	0	559	1204	46.42857	0.7197	0	346	1440	24.02778	0.8306	1	469	1942	24.15036	0.9360	1	363	16.470054	0.7020	0	578	26.22505	0.74410	0	442	1558	28.36970	0.9675	1	247	396	62.373737	0.9898	1	104	2051	5.070697	0.7260	0	2118	2204	96.09800	0.9204	1	1204	570	47.342193	0.8858	1	0	0.0000000	0.3251	14	1204	1.162791	0.4877	0	817	1204	67.85714	0.9413	1	0	2204	0.000000	0.3512	0	4.4150	0.9451	4	4.12940	0.9805	2	0.9204	0.9114	1	2.9911	0.7243	2	12.45590	0.9597	9	1950	1267	1096	1131	1950	58.00000	0.9678	1	66	706	9.348442	0.8395	1	42	101	41.58416	0.8612	1	309	995	31.05528	0.1959	0	351	1096	32.02555	0.4782	0	510	1379	36.98332	0.9763	1	155	1950	7.948718	0.7660	1	392	20.102564	0.69880	447	22.92308	0.6712	0	570	1503	37.924152	0.99200	1	143	374	38.23529	0.9167	1	109	1841	5.920695	0.7464	0	1909	1950	97.89744	0.9529	1	1267	479	37.8058406	0.8464	1	0	0.0000000	0.3216	33	1096	3.010949	0.6446	0	743	1096	67.79197	0.9414	1	0	1950	0.0000000	0.1517	4.0278	0.8848	4	4.02510	0.9798	2	0.9529	0.9442	1	2.9057	0.6869	2	11.91150	0.9365	9	1	0

Code

svi_national_lihtc10 <- left_join(svi_national, lihtc_projects10, join_by("GEOID_2010_trt" == "fips2010"))

svi_national_lihtc10 %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID_2010_trt	FIPS_st	FIPS_county	FIPS_tract	state	state_name	county	region_number	region	division_number	division	E_TOTPOP_10	E_HU_10	E_HH_10	E_POV150_10	ET_POVSTATUS_10	EP_POV150_10	EPL_POV150_10	E_UNEMP_10	ET_EMPSTATUS_10	EP_UNEMP_10	EPL_UNEMP_10	E_HBURD_OWN_10	ET_HOUSINGCOST_OWN_10	EP_HBURD_OWN_10	EPL_HBURD_OWN_10	E_HBURD_RENT_10	ET_HOUSINGCOST_RENT_10	EP_HBURD_RENT_10	EPL_HBURD_RENT_10	E_HBURD_10	ET_HOUSINGCOST_10	EP_HBURD_10	EPL_HBURD_10	E_NOHSDP_10	ET_EDSTATUS_10	EP_NOHSDP_10	EPL_NOHSDP_10	F_NOHSDP_10	E_UNINSUR_12	ET_INSURSTATUS_12	EP_UNINSUR_12	EPL_UNINSUR_12	E_AGE65_10	EP_AGE65_10	EPL_AGE65_10	F_AGE65_10	E_AGE17_10	EP_AGE17_10	EPL_AGE17_10	F_AGE17_10	E_DISABL_12	ET_DISABLSTATUS_12	EP_DISABL_12	EPL_DISABL_12	F_DISABL_12	E_SNGPNT_10	ET_FAMILIES_10	EP_SNGPNT_10	EPL_SNGPNT_10	F_SNGPNT_10	E_LIMENG_10	ET_POPAGE5UP_10	EP_LIMENG_10	EPL_LIMENG_10	E_MINRTY_10	ET_POPETHRACE_10	EP_MINRTY_10	EPL_MINRTY_10	F_MINRTY_10	E_STRHU_10	E_MUNIT_10	EP_MUNIT_10	EPL_MUNIT_10	E_MOBILE_10	EP_MOBILE_10	EPL_MOBILE_10	F_MOBILE_10	E_CROWD_10	ET_OCCUPANTS_10	EP_CROWD_10	EPL_CROWD_10	E_NOVEH_10	ET_KNOWNVEH_10	EP_NOVEH_10	EPL_NOVEH_10	F_NOVEH_10	ET_HHTYPE_10	EPL_GROUPQ_10	SPL_THEME1_10	RPL_THEME1_10	F_THEME1_10	SPL_THEME2_10	RPL_THEME2_10	F_THEME2_10	SPL_THEME3_10	RPL_THEME3_10	F_THEME3_10	SPL_THEME4_10	RPL_THEME4_10	F_THEME4_10	SPL_THEMES_10	RPL_THEMES_10	F_TOTAL_10	E_TOTPOP_20	E_HU_20	E_HH_20	E_POV150_20	ET_POVSTATUS_20	EP_POV150_20	EPL_POV150_20	F_POV150_20	E_UNEMP_20	ET_EMPSTATUS_20	EP_UNEMP_20	EPL_UNEMP_20	E_HBURD_OWN_20	ET_HOUSINGCOST_OWN_20	EP_HBURD_OWN_20	EPL_HBURD_OWN_20	F_HBURD_OWN_20	E_HBURD_RENT_20	ET_HOUSINGCOST_RENT_20	EP_HBURD_RENT_20	EPL_HBURD_RENT_20	F_HBURD_RENT_20	E_HBURD_20	ET_HOUSINGCOST_20	EP_HBURD_20	EPL_HBURD_20	E_NOHSDP_20	ET_EDSTATUS_20	EP_NOHSDP_20	EPL_NOHSDP_20	E_UNINSUR_20	ET_INSURSTATUS_20	EP_UNINSUR_20	EPL_UNINSUR_20	F_UNINSUR_20	E_AGE65_20	EP_AGE65_20	EPL_AGE65_20	F_AGE65_20	E_AGE17_20	EP_AGE17_20	EPL_AGE17_20	F_AGE17_20	E_DISABL_20	ET_DISABLSTATUS_20	EP_DISABL_20	EPL_DISABL_20	F_DISABL_20	E_SNGPNT_20	ET_FAMILIES_20	EP_SNGPNT_20	EPL_SNGPNT_20	F_SNGPNT_20	E_LIMENG_20	ET_POPAGE5UP_20	EP_LIMENG_20	EPL_LIMENG_20	E_MINRTY_20	ET_POPETHRACE_20	EP_MINRTY_20	EPL_MINRTY_20	F_MINRTY_20	E_STRHU_20	E_MUNIT_20	EP_MUNIT_20	EPL_MUNIT_20	E_MOBILE_20	EP_MOBILE_20	EPL_MOBILE_20	F_MOBILE_20	E_CROWD_20	ET_OCCUPANTS_20	EP_CROWD_20	EPL_CROWD_20	E_NOVEH_20	ET_KNOWNVEH_20	EP_NOVEH_20	EPL_NOVEH_20	E_GROUPQ_20	ET_HHTYPE_20	EP_GROUPQ_20	EPL_GROUPQ_20	F_GROUPQ_20	SPL_THEME1_20	RPL_THEME1_20	F_THEME1_20	SPL_THEME2_20	RPL_THEME2_20	F_THEME2_20	SPL_THEME3_20	RPL_THEME3_20	F_THEME3_20	SPL_THEME4_20	RPL_THEME4_20	F_THEME4_20	SPL_THEMES_20	RPL_THEMES_20	F_TOTAL_20	pre10_lihtc_project_cnt	pre10_lihtc_project_dollars
01001020100	01	001	020100	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	1809	771	696	297	1809	16.41791	0.3871	36	889	4.049494	0.1790	127	598	21.23746	0.20770	47	98	47.95918	0.5767	174	696	25.00000	0.18790	196	1242	15.780998	0.6093	0	186	1759	10.574190	0.3790	222	12.271973	0.4876	0	445	24.59923	0.5473	0	298	1335	22.32210	0.8454	1	27	545	4.954128	0.09275	0	36	1705	2.1114370	0.59040	385	1809	21.282477	0.4524	0	771	0	0.0000000	0.1224	92	11.9325551	0.8005	1	0	696	0.0000000	0.1238	50	696	7.183908	0.6134	0	1809	0.364	1.74230	0.28200	0	2.56345	0.5296	1	0.4524	0.4482	0	2.0241	0.2519	1	6.78225	0.3278	2	1941	710	693	352	1941	18.13498	0.4630	0	18	852	2.112676	0.15070	81	507	15.976331	0.26320	0	63	186	33.87097	0.2913	0	144	693	20.77922	0.2230	187	1309	14.285714	0.6928	187	1941	9.634209	0.6617	0	295	15.19835	0.4601	0	415	21.38073	0.4681	0	391	1526	25.62254	0.9011	1	58	555	10.45045	0.3451	0	0	1843	0.0000000	0.09479	437	1941	22.51417	0.3902	0	710	0	0.0000000	0.1079	88	12.3943662	0.8263	1	0	693	0.0000000	0.09796	10	693	1.443001	0.1643	0	1941	0.000000	0.1831	0	2.19120	0.4084	0	2.26919	0.3503	1	0.3902	0.3869	0	1.37956	0.07216	1	6.23015	0.2314	2	NA	NA
01001020200	01	001	020200	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	2020	816	730	495	1992	24.84940	0.5954	68	834	8.153477	0.5754	49	439	11.16173	0.02067	105	291	36.08247	0.3019	154	730	21.09589	0.09312	339	1265	26.798419	0.8392	1	313	2012	15.556660	0.6000	204	10.099010	0.3419	0	597	29.55446	0.8192	1	359	1515	23.69637	0.8791	1	132	456	28.947368	0.83510	1	15	1890	0.7936508	0.40130	1243	2020	61.534653	0.7781	1	816	0	0.0000000	0.1224	34	4.1666667	0.6664	0	13	730	1.7808219	0.5406	115	730	15.753425	0.8382	1	2020	0.364	2.70312	0.56650	1	3.27660	0.8614	3	0.7781	0.7709	1	2.5316	0.5047	1	9.28942	0.6832	6	1757	720	573	384	1511	25.41363	0.6427	0	29	717	4.044630	0.41320	33	392	8.418367	0.03542	0	116	181	64.08840	0.9086	1	149	573	26.00349	0.4041	139	1313	10.586443	0.5601	91	1533	5.936073	0.4343	0	284	16.16392	0.5169	0	325	18.49744	0.2851	0	164	1208	13.57616	0.4127	0	42	359	11.69916	0.3998	0	0	1651	0.0000000	0.09479	1116	1757	63.51736	0.7591	1	720	3	0.4166667	0.2470	5	0.6944444	0.5106	0	9	573	1.5706806	0.46880	57	573	9.947644	0.7317	212	1757	12.066022	0.9549	1	2.45440	0.4888	0	1.70929	0.1025	0	0.7591	0.7527	1	2.91300	0.68620	1	7.83579	0.4802	2	NA	NA
01001020300	01	001	020300	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	3543	1403	1287	656	3533	18.56779	0.4443	93	1552	5.992268	0.3724	273	957	28.52665	0.45780	178	330	53.93939	0.7152	451	1287	35.04274	0.49930	346	2260	15.309734	0.5950	0	252	3102	8.123791	0.2596	487	13.745413	0.5868	0	998	28.16822	0.7606	1	371	2224	16.68165	0.6266	0	126	913	13.800657	0.46350	0	0	3365	0.0000000	0.09298	637	3543	17.979114	0.4049	0	1403	10	0.7127584	0.3015	2	0.1425517	0.4407	0	0	1287	0.0000000	0.1238	101	1287	7.847708	0.6443	0	3543	0.364	2.17060	0.41010	0	2.53048	0.5116	1	0.4049	0.4011	0	1.8743	0.1942	0	6.98028	0.3576	1	3694	1464	1351	842	3694	22.79372	0.5833	0	53	1994	2.657974	0.22050	117	967	12.099276	0.11370	0	147	384	38.28125	0.3856	0	264	1351	19.54108	0.1827	317	2477	12.797739	0.6460	127	3673	3.457664	0.2308	0	464	12.56091	0.3088	0	929	25.14889	0.7080	0	473	2744	17.23761	0.6211	0	263	975	26.97436	0.8234	1	128	3586	3.5694367	0.70770	1331	3694	36.03140	0.5515	0	1464	26	1.7759563	0.3675	14	0.9562842	0.5389	0	35	1351	2.5906736	0.60550	42	1351	3.108808	0.3415	0	3694	0.000000	0.1831	0	1.86330	0.3063	0	3.16900	0.8380	1	0.5515	0.5468	0	2.03650	0.26830	0	7.62030	0.4460	1	2	216593
01001020400	01	001	020400	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	4840	1957	1839	501	4840	10.35124	0.2177	101	2129	4.744011	0.2447	310	1549	20.01291	0.17080	89	290	30.68966	0.2044	399	1839	21.69657	0.10540	274	3280	8.353658	0.3205	0	399	4293	9.294200	0.3171	955	19.731405	0.8643	1	1195	24.69008	0.5530	0	625	3328	18.78005	0.7233	0	152	1374	11.062591	0.34710	0	10	4537	0.2204100	0.22560	297	4840	6.136364	0.1647	0	1957	33	1.6862545	0.3843	25	1.2774655	0.5516	0	14	1839	0.7612833	0.3564	19	1839	1.033170	0.1127	0	4840	0.364	1.20540	0.13470	0	2.71330	0.6129	1	0.1647	0.1632	0	1.7690	0.1591	0	5.85240	0.1954	1	3539	1741	1636	503	3539	14.21305	0.3472	0	39	1658	2.352232	0.17990	219	1290	16.976744	0.30880	0	74	346	21.38728	0.1037	0	293	1636	17.90954	0.1333	173	2775	6.234234	0.3351	169	3529	4.788892	0.3448	0	969	27.38062	0.9225	1	510	14.41085	0.1208	0	670	3019	22.19278	0.8194	1	148	1137	13.01671	0.4541	0	89	3409	2.6107363	0.64690	454	3539	12.82848	0.2364	0	1741	143	8.2136703	0.6028	0	0.0000000	0.2186	0	10	1636	0.6112469	0.28340	72	1636	4.400978	0.4538	0	3539	0.000000	0.1831	0	1.34030	0.1575	0	2.96370	0.7496	2	0.2364	0.2344	0	1.74170	0.16270	0	6.28210	0.2389	2	NA	NA
01001020500	01	001	020500	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	9938	3969	3741	1096	9938	11.02838	0.2364	188	4937	3.807981	0.1577	426	2406	17.70574	0.11050	528	1335	39.55056	0.3753	954	3741	25.50120	0.20140	293	5983	4.897209	0.1655	0	740	10110	7.319486	0.2211	837	8.422218	0.2408	0	3012	30.30791	0.8455	1	759	7155	10.60797	0.2668	0	476	2529	18.821669	0.63540	0	78	9297	0.8389803	0.41110	1970	9938	19.822902	0.4330	0	3969	306	7.7097506	0.6153	0	0.0000000	0.2198	0	7	3741	0.1871157	0.2535	223	3741	5.960973	0.5483	0	9938	0.364	0.98210	0.08468	0	2.39960	0.4381	1	0.4330	0.4290	0	2.0009	0.2430	0	5.81560	0.1905	1	10674	4504	4424	1626	10509	15.47245	0.3851	0	81	5048	1.604596	0.09431	321	2299	13.962592	0.17970	0	711	2125	33.45882	0.2836	0	1032	4424	23.32731	0.3109	531	6816	7.790493	0.4251	301	10046	2.996217	0.1894	0	1613	15.11149	0.4553	0	2765	25.90407	0.7494	0	1124	7281	15.43744	0.5253	0	342	2912	11.74451	0.4019	0	52	9920	0.5241935	0.35230	2603	10674	24.38636	0.4160	0	4504	703	15.6083481	0.7378	29	0.6438721	0.5037	0	37	4424	0.8363472	0.33420	207	4424	4.679023	0.4754	176	10674	1.648866	0.7598	1	1.40481	0.1743	0	2.48420	0.4802	0	0.4160	0.4125	0	2.81090	0.63730	1	7.11591	0.3654	1	5	2250459
01001020600	01	001	020600	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	3402	1456	1308	735	3402	21.60494	0.5199	134	1720	7.790698	0.5436	242	1032	23.44961	0.28010	62	276	22.46377	0.1035	304	1308	23.24159	0.14070	301	2151	13.993491	0.5510	0	355	3445	10.304790	0.3656	386	11.346267	0.4232	0	931	27.36626	0.7200	0	440	2439	18.04018	0.6912	0	143	924	15.476190	0.52900	0	4	3254	0.1229256	0.19840	723	3402	21.252205	0.4519	0	1456	18	1.2362637	0.3507	433	29.7390110	0.9468	1	16	1308	1.2232416	0.4493	28	1308	2.140673	0.2298	0	3402	0.364	2.12080	0.39510	0	2.56180	0.5288	0	0.4519	0.4477	0	2.3406	0.4048	1	7.47510	0.4314	1	3536	1464	1330	1279	3523	36.30429	0.8215	1	34	1223	2.780049	0.23780	321	1111	28.892889	0.75870	1	67	219	30.59361	0.2305	0	388	1330	29.17293	0.5075	306	2380	12.857143	0.6480	415	3496	11.870709	0.7535	1	547	15.46946	0.4760	0	982	27.77149	0.8327	1	729	2514	28.99761	0.9488	1	95	880	10.79545	0.3601	0	0	3394	0.0000000	0.09479	985	3536	27.85633	0.4608	0	1464	0	0.0000000	0.1079	364	24.8633880	0.9300	1	0	1330	0.0000000	0.09796	17	1330	1.278196	0.1463	0	3536	0.000000	0.1831	0	2.96830	0.6434	2	2.71239	0.6156	2	0.4608	0.4569	0	1.46526	0.08976	1	7.60675	0.4440	5	NA	NA

We will add in our 2020 data:

Code

svi_divisional_lihtc20 <- left_join(svi_divisional_lihtc10, lihtc_projects20, join_by("GEOID_2010_trt" == "fips2010"))

svi_divisional_lihtc20 %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID_2010_trt	FIPS_st	FIPS_county	FIPS_tract	state	state_name	county	region_number	region	division_number	division	E_TOTPOP_10	E_HU_10	E_HH_10	E_POV150_10	ET_POVSTATUS_10	EP_POV150_10	EPL_POV150_10	F_POV150_10	E_UNEMP_10	ET_EMPSTATUS_10	EP_UNEMP_10	EPL_UNEMP_10	F_UNEMP_10	E_HBURD_OWN_10	ET_HOUSINGCOST_OWN_10	EP_HBURD_OWN_10	EPL_HBURD_OWN_10	F_HBURD_OWN_10	E_HBURD_RENT_10	ET_HOUSINGCOST_RENT_10	EP_HBURD_RENT_10	EPL_HBURD_RENT_10	F_HBURD_RENT_10	E_HBURD_10	ET_HOUSINGCOST_10	EP_HBURD_10	EPL_HBURD_10	F_HBURD_10	E_NOHSDP_10	ET_EDSTATUS_10	EP_NOHSDP_10	EPL_NOHSDP_10	F_NOHSDP_10	E_UNINSUR_12	ET_INSURSTATUS_12	EP_UNINSUR_12	EPL_UNINSUR_12	F_UNINSUR_12	E_AGE65_10	EP_AGE65_10	EPL_AGE65_10	F_AGE65_10	E_AGE17_10	EP_AGE17_10	EPL_AGE17_10	F_AGE17_10	E_DISABL_12	ET_DISABLSTATUS_12	EP_DISABL_12	EPL_DISABL_12	F_DISABL_12	E_SNGPNT_10	ET_FAMILIES_10	EP_SNGPNT_10	EPL_SNGPNT_10	F_SNGPNT_10	E_LIMENG_10	ET_POPAGE5UP_10	EP_LIMENG_10	EPL_LIMENG_10	F_LIMENG_10	E_MINRTY_10	ET_POPETHRACE_10	EP_MINRTY_10	EPL_MINRTY_10	F_MINRTY_10	E_STRHU_10	E_MUNIT_10	EP_MUNIT_10	EPL_MUNIT_10	F_MUNIT_10	E_MOBILE_10	EP_MOBILE_10	EPL_MOBILE_10	E_CROWD_10	ET_OCCUPANTS_10	EP_CROWD_10	EPL_CROWD_10	F_CROWD_10	E_NOVEH_10	ET_KNOWNVEH_10	EP_NOVEH_10	EPL_NOVEH_10	F_NOVEH_10	E_GROUPQ_10	ET_HHTYPE_10	EP_GROUPQ_10	EPL_GROUPQ_10	F_GROUPQ_10	SPL_THEME1_10	RPL_THEME1_10	F_THEME1_10	SPL_THEME2_10	RPL_THEME2_10	F_THEME2_10	SPL_THEME3_10	RPL_THEME3_10	F_THEME3_10	SPL_THEME4_10	RPL_THEME4_10	F_THEME4_10	SPL_THEMES_10	RPL_THEMES_10	F_TOTAL_10	E_TOTPOP_20	E_HU_20	E_HH_20	E_POV150_20	ET_POVSTATUS_20	EP_POV150_20	EPL_POV150_20	F_POV150_20	E_UNEMP_20	ET_EMPSTATUS_20	EP_UNEMP_20	EPL_UNEMP_20	F_UNEMP_20	E_HBURD_OWN_20	ET_HOUSINGCOST_OWN_20	EP_HBURD_OWN_20	EPL_HBURD_OWN_20	F_HBURD_OWN_20	E_HBURD_RENT_20	ET_HOUSINGCOST_RENT_20	EP_HBURD_RENT_20	EPL_HBURD_RENT_20	F_HBURD_RENT_20	E_HBURD_20	ET_HOUSINGCOST_20	EP_HBURD_20	EPL_HBURD_20	F_HBURD_20	E_NOHSDP_20	ET_EDSTATUS_20	EP_NOHSDP_20	EPL_NOHSDP_20	F_NOHSDP_20	E_UNINSUR_20	ET_INSURSTATUS_20	EP_UNINSUR_20	EPL_UNINSUR_20	F_UNINSUR_20	E_AGE65_20	EP_AGE65_20	EPL_AGE65_20	E_AGE17_20	EP_AGE17_20	EPL_AGE17_20	F_AGE17_20	E_DISABL_20	ET_DISABLSTATUS_20	EP_DISABL_20	EPL_DISABL_20	F_DISABL_20	E_SNGPNT_20	ET_FAMILIES_20	EP_SNGPNT_20	EPL_SNGPNT_20	F_SNGPNT_20	E_LIMENG_20	ET_POPAGE5UP_20	EP_LIMENG_20	EPL_LIMENG_20	F_LIMENG_20	E_MINRTY_20	ET_POPETHRACE_20	EP_MINRTY_20	EPL_MINRTY_20	F_MINRTY_20	E_STRHU_20	E_MUNIT_20	EP_MUNIT_20	EPL_MUNIT_20	F_MUNIT_20	E_MOBILE_20	EP_MOBILE_20	EPL_MOBILE_20	E_CROWD_20	ET_OCCUPANTS_20	EP_CROWD_20	EPL_CROWD_20	F_CROWD_20	E_NOVEH_20	ET_KNOWNVEH_20	EP_NOVEH_20	EPL_NOVEH_20	F_NOVEH_20	E_GROUPQ_20	ET_HHTYPE_20	EP_GROUPQ_20	EPL_GROUPQ_20	SPL_THEME1_20	RPL_THEME1_20	F_THEME1_20	SPL_THEME2_20	RPL_THEME2_20	F_THEME2_20	SPL_THEME3_20	RPL_THEME3_20	F_THEME3_20	SPL_THEME4_20	RPL_THEME4_20	F_THEME4_20	SPL_THEMES_20	RPL_THEMES_20	F_TOTAL_20	pre10_lihtc_project_cnt	pre10_lihtc_project_dollars	post10_lihtc_project_cnt	post10_lihtc_project_dollars
34001000100	34	001	000100	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2907	1088	983	1127	2907	38.76849	0.8482	1	144	1433	10.048849	0.7544	1	280	435	64.36782	0.9529	1	204	548	37.22628	0.2998	0	484	983	49.23703	0.7813	1	468	1759	26.60603	0.8634	1	532	2543	20.92017	0.8978	1	250	8.599931	0.1777	0	944	32.47334	0.94170	1	186	1851	10.04862	0.2706	0	266	678	39.233038	0.8981	1	177	2611	6.779012	0.7778	1	1928	2907	66.32267	0.7743	1	1088	113	10.386029	0.6229	0	9	0.8272059	0.7223	80	983	8.138352	0.8657	1	265	983	26.95829	0.7354	0	0	2907	0.000000	0.3512	0	4.1451	0.8935	5	3.06590	0.7944	3	0.7743	0.7667	1	3.2975	0.8414	1	11.28280	0.8862	10	2157	941	784	1182	2157	54.79833	0.9571	1	242	1058	22.873346	0.9922	1	215	342	62.86550	0.9780	1	316	442	71.49321	0.9481	1	531	784	67.72959	0.9893	1	396	1274	31.08320	0.9497	1	266	2157	12.331943	0.9041	1	185	8.576727	0.09430	552	25.59110	0.8128	1	297	1605	18.504673	0.74880	0	83	510	16.27451	0.6090	0	251	2020	12.425743	0.8710	1	1852	2157	85.85999	0.8476	1	941	118	12.5398512	0.6385	0	0	0.0000000	0.3216	67	784	8.545918	0.8657	1	212	784	27.04082	0.7502	1	0	2157	0.0000000	0.1517	4.7924	0.9850	5	3.13590	0.8217	2	0.8476	0.8400	1	2.7277	0.6085	2	11.50360	0.9104	10	NA	NA	NA	NA
34001000200	34	001	000200	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3189	2217	1473	519	3189	16.27469	0.4806	0	109	1558	6.996149	0.5179	0	573	955	60.00000	0.9323	1	199	518	38.41699	0.3261	0	772	1473	52.41005	0.8418	1	405	2579	15.70376	0.6491	0	484	3547	13.64533	0.7154	0	847	26.560050	0.9629	1	436	13.67200	0.08181	0	608	3005	20.23295	0.8466	1	42	857	4.900817	0.1204	0	422	3072	13.736979	0.8799	1	1792	3189	56.19316	0.7390	0	2217	901	40.640505	0.8693	1	0	0.0000000	0.3251	48	1473	3.258656	0.7064	0	250	1473	16.97217	0.6444	0	0	3189	0.000000	0.3512	0	3.2048	0.6963	1	2.89161	0.7231	3	0.7390	0.7317	0	2.8964	0.6887	1	9.73181	0.7340	5	3510	2046	1353	1021	3510	29.08832	0.7682	1	121	1852	6.533477	0.6717	0	343	696	49.28161	0.9273	1	416	657	63.31811	0.8696	1	759	1353	56.09756	0.9321	1	553	2338	23.65269	0.8871	1	354	3510	10.085470	0.8530	1	643	18.319088	0.60310	1002	28.54701	0.9055	1	450	2508	17.942584	0.72330	0	237	786	30.15267	0.8539	1	534	3375	15.822222	0.9062	1	2534	3510	72.19373	0.7818	1	2046	906	44.2815249	0.8690	1	0	0.0000000	0.3216	119	1353	8.795270	0.8711	1	324	1353	23.94678	0.7255	0	0	3510	0.0000000	0.1517	4.1121	0.9003	4	3.99200	0.9781	3	0.7818	0.7747	1	2.9389	0.7011	2	11.82480	0.9310	10	NA	NA	NA	NA
34001000300	34	001	000300	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3997	1823	1357	1401	3968	35.30746	0.8164	1	382	2238	17.068811	0.9376	1	176	329	53.49544	0.8855	1	604	1028	58.75486	0.7947	1	780	1357	57.47973	0.9165	1	920	2677	34.36683	0.9346	1	1351	4149	32.56206	0.9811	1	314	7.855892	0.1437	0	937	23.44258	0.55900	0	319	3054	10.44532	0.3000	0	187	782	23.913044	0.7498	0	1080	3671	29.419777	0.9742	1	3357	3997	83.98799	0.8419	1	1823	363	19.912233	0.7535	1	0	0.0000000	0.3251	150	1357	11.053795	0.9136	1	651	1357	47.97347	0.8585	1	0	3997	0.000000	0.3512	0	4.5862	0.9691	5	2.72670	0.6360	1	0.8419	0.8336	1	3.2019	0.8054	3	11.35670	0.8920	10	3801	1640	1226	1857	3801	48.85556	0.9333	1	226	1800	12.555556	0.9267	1	111	280	39.64286	0.8339	1	608	946	64.27061	0.8842	1	719	1226	58.64600	0.9528	1	650	2275	28.57143	0.9337	1	1027	3801	27.019206	0.9914	1	380	9.997369	0.14040	1223	32.17574	0.9607	1	219	2578	8.494957	0.15680	0	268	909	29.48295	0.8456	1	940	3400	27.647059	0.9728	1	3318	3801	87.29282	0.8579	1	1640	262	15.9756098	0.6917	0	0	0.0000000	0.3216	124	1226	10.114192	0.8955	1	477	1226	38.90701	0.8258	1	0	3801	0.0000000	0.1517	4.7379	0.9829	5	3.07630	0.8013	3	0.8579	0.8501	1	2.8863	0.6781	2	11.55840	0.9150	11	NA	NA	NA	NA
34001000400	34	001	000400	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2902	2683	1401	1172	2902	40.38594	0.8615	1	190	1389	13.678906	0.8811	1	364	707	51.48515	0.8627	1	507	694	73.05476	0.9503	1	871	1401	62.16988	0.9572	1	481	1981	24.28067	0.8339	1	674	3204	21.03620	0.8998	1	434	14.955203	0.6083	0	596	20.53756	0.33980	0	426	2607	16.34062	0.6886	0	111	652	17.024540	0.6204	0	215	2736	7.858187	0.8008	1	1792	2902	61.75052	0.7584	1	2683	2049	76.369735	0.9401	1	0	0.0000000	0.3251	69	1401	4.925053	0.7847	1	511	1401	36.47395	0.7992	1	72	2902	2.481048	0.8114	1	4.4335	0.9468	5	3.05790	0.7908	1	0.7584	0.7510	1	3.6605	0.9391	4	11.91030	0.9339	11	3178	2264	1390	1508	3176	47.48111	0.9246	1	172	1804	9.534368	0.8460	1	205	468	43.80342	0.8858	1	622	922	67.46204	0.9192	1	827	1390	59.49640	0.9587	1	364	2076	17.53372	0.8013	1	476	3178	14.977974	0.9390	1	483	15.198238	0.41220	539	16.96035	0.2484	0	319	2639	12.087912	0.38790	0	101	565	17.87611	0.6539	0	583	3022	19.291860	0.9349	1	2186	3178	68.78540	0.7658	1	2264	1609	71.0689046	0.9266	1	15	0.6625442	0.7078	226	1390	16.258993	0.9567	1	599	1390	43.09353	0.8474	1	20	3178	0.6293266	0.6292	4.4696	0.9558	5	2.63730	0.5864	1	0.7658	0.7588	1	4.0677	0.9762	3	11.94040	0.9387	10	NA	NA	NA	NA
34001000500	34	001	000500	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3483	1241	1027	1938	3483	55.64169	0.9533	1	124	1630	7.607362	0.5830	0	227	446	50.89686	0.8549	1	478	581	82.27194	0.9799	1	705	1027	68.64654	0.9863	1	733	2077	35.29129	0.9396	1	727	3258	22.31430	0.9149	1	377	10.824002	0.3081	0	1055	30.28998	0.90140	1	268	2401	11.16202	0.3549	0	209	763	27.391874	0.7940	1	911	3077	29.606760	0.9746	1	3036	3483	87.16624	0.8550	1	1241	52	4.190169	0.4505	0	4	0.3223207	0.6567	113	1027	11.002921	0.9128	1	422	1027	41.09056	0.8250	1	0	3483	0.000000	0.3512	0	4.3771	0.9379	4	3.33300	0.8766	3	0.8550	0.8467	1	3.1962	0.8026	2	11.76130	0.9229	10	3385	1185	945	1682	3364	50.00000	0.9391	1	72	1577	4.565631	0.4586	0	185	468	39.52991	0.8332	1	362	477	75.89099	0.9703	1	547	945	57.88360	0.9477	1	592	1983	29.85376	0.9422	1	738	3385	21.802068	0.9817	1	240	7.090103	0.05988	1129	33.35303	0.9689	1	135	2256	5.984043	0.04817	0	110	717	15.34170	0.5822	0	721	3076	23.439532	0.9569	1	3029	3385	89.48301	0.8727	1	1185	9	0.7594937	0.2382	0	0	0.0000000	0.3216	103	945	10.899471	0.9072	1	263	945	27.83069	0.7560	1	0	3385	0.0000000	0.1517	4.2693	0.9283	4	2.61605	0.5709	2	0.8727	0.8648	1	2.3747	0.4357	2	10.13275	0.7921	9	NA	NA	NA	NA
34001001100	34	001	001100	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2204	1204	1204	1185	2204	53.76588	0.9457	1	219	927	23.624596	0.9830	1	97	172	56.39535	0.9094	1	462	1032	44.76744	0.4746	0	559	1204	46.42857	0.7197	0	346	1440	24.02778	0.8306	1	469	1942	24.15036	0.9360	1	363	16.470054	0.7020	0	578	26.22505	0.74410	0	442	1558	28.36970	0.9675	1	247	396	62.373737	0.9898	1	104	2051	5.070697	0.7260	0	2118	2204	96.09800	0.9204	1	1204	570	47.342193	0.8858	1	0	0.0000000	0.3251	14	1204	1.162791	0.4877	0	817	1204	67.85714	0.9413	1	0	2204	0.000000	0.3512	0	4.4150	0.9451	4	4.12940	0.9805	2	0.9204	0.9114	1	2.9911	0.7243	2	12.45590	0.9597	9	1950	1267	1096	1131	1950	58.00000	0.9678	1	66	706	9.348442	0.8395	1	42	101	41.58416	0.8612	1	309	995	31.05528	0.1959	0	351	1096	32.02555	0.4782	0	510	1379	36.98332	0.9763	1	155	1950	7.948718	0.7660	1	392	20.102564	0.69880	447	22.92308	0.6712	0	570	1503	37.924152	0.99200	1	143	374	38.23529	0.9167	1	109	1841	5.920695	0.7464	0	1909	1950	97.89744	0.9529	1	1267	479	37.8058406	0.8464	1	0	0.0000000	0.3216	33	1096	3.010949	0.6446	0	743	1096	67.79197	0.9414	1	0	1950	0.0000000	0.1517	4.0278	0.8848	4	4.02510	0.9798	2	0.9529	0.9442	1	2.9057	0.6869	2	11.91150	0.9365	9	1	0	1	1290441

Code

svi_national_lihtc20 <- left_join(svi_national_lihtc10, lihtc_projects20, join_by("GEOID_2010_trt" == "fips2010"))

svi_national_lihtc20 %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID_2010_trt	FIPS_st	FIPS_county	FIPS_tract	state	state_name	county	region_number	region	division_number	division	E_TOTPOP_10	E_HU_10	E_HH_10	E_POV150_10	ET_POVSTATUS_10	EP_POV150_10	EPL_POV150_10	E_UNEMP_10	ET_EMPSTATUS_10	EP_UNEMP_10	EPL_UNEMP_10	E_HBURD_OWN_10	ET_HOUSINGCOST_OWN_10	EP_HBURD_OWN_10	EPL_HBURD_OWN_10	E_HBURD_RENT_10	ET_HOUSINGCOST_RENT_10	EP_HBURD_RENT_10	EPL_HBURD_RENT_10	E_HBURD_10	ET_HOUSINGCOST_10	EP_HBURD_10	EPL_HBURD_10	E_NOHSDP_10	ET_EDSTATUS_10	EP_NOHSDP_10	EPL_NOHSDP_10	F_NOHSDP_10	E_UNINSUR_12	ET_INSURSTATUS_12	EP_UNINSUR_12	EPL_UNINSUR_12	E_AGE65_10	EP_AGE65_10	EPL_AGE65_10	F_AGE65_10	E_AGE17_10	EP_AGE17_10	EPL_AGE17_10	F_AGE17_10	E_DISABL_12	ET_DISABLSTATUS_12	EP_DISABL_12	EPL_DISABL_12	F_DISABL_12	E_SNGPNT_10	ET_FAMILIES_10	EP_SNGPNT_10	EPL_SNGPNT_10	F_SNGPNT_10	E_LIMENG_10	ET_POPAGE5UP_10	EP_LIMENG_10	EPL_LIMENG_10	E_MINRTY_10	ET_POPETHRACE_10	EP_MINRTY_10	EPL_MINRTY_10	F_MINRTY_10	E_STRHU_10	E_MUNIT_10	EP_MUNIT_10	EPL_MUNIT_10	E_MOBILE_10	EP_MOBILE_10	EPL_MOBILE_10	F_MOBILE_10	E_CROWD_10	ET_OCCUPANTS_10	EP_CROWD_10	EPL_CROWD_10	E_NOVEH_10	ET_KNOWNVEH_10	EP_NOVEH_10	EPL_NOVEH_10	F_NOVEH_10	ET_HHTYPE_10	EPL_GROUPQ_10	SPL_THEME1_10	RPL_THEME1_10	F_THEME1_10	SPL_THEME2_10	RPL_THEME2_10	F_THEME2_10	SPL_THEME3_10	RPL_THEME3_10	F_THEME3_10	SPL_THEME4_10	RPL_THEME4_10	F_THEME4_10	SPL_THEMES_10	RPL_THEMES_10	F_TOTAL_10	E_TOTPOP_20	E_HU_20	E_HH_20	E_POV150_20	ET_POVSTATUS_20	EP_POV150_20	EPL_POV150_20	F_POV150_20	E_UNEMP_20	ET_EMPSTATUS_20	EP_UNEMP_20	EPL_UNEMP_20	E_HBURD_OWN_20	ET_HOUSINGCOST_OWN_20	EP_HBURD_OWN_20	EPL_HBURD_OWN_20	F_HBURD_OWN_20	E_HBURD_RENT_20	ET_HOUSINGCOST_RENT_20	EP_HBURD_RENT_20	EPL_HBURD_RENT_20	F_HBURD_RENT_20	E_HBURD_20	ET_HOUSINGCOST_20	EP_HBURD_20	EPL_HBURD_20	E_NOHSDP_20	ET_EDSTATUS_20	EP_NOHSDP_20	EPL_NOHSDP_20	E_UNINSUR_20	ET_INSURSTATUS_20	EP_UNINSUR_20	EPL_UNINSUR_20	F_UNINSUR_20	E_AGE65_20	EP_AGE65_20	EPL_AGE65_20	F_AGE65_20	E_AGE17_20	EP_AGE17_20	EPL_AGE17_20	F_AGE17_20	E_DISABL_20	ET_DISABLSTATUS_20	EP_DISABL_20	EPL_DISABL_20	F_DISABL_20	E_SNGPNT_20	ET_FAMILIES_20	EP_SNGPNT_20	EPL_SNGPNT_20	F_SNGPNT_20	E_LIMENG_20	ET_POPAGE5UP_20	EP_LIMENG_20	EPL_LIMENG_20	E_MINRTY_20	ET_POPETHRACE_20	EP_MINRTY_20	EPL_MINRTY_20	F_MINRTY_20	E_STRHU_20	E_MUNIT_20	EP_MUNIT_20	EPL_MUNIT_20	E_MOBILE_20	EP_MOBILE_20	EPL_MOBILE_20	F_MOBILE_20	E_CROWD_20	ET_OCCUPANTS_20	EP_CROWD_20	EPL_CROWD_20	E_NOVEH_20	ET_KNOWNVEH_20	EP_NOVEH_20	EPL_NOVEH_20	E_GROUPQ_20	ET_HHTYPE_20	EP_GROUPQ_20	EPL_GROUPQ_20	F_GROUPQ_20	SPL_THEME1_20	RPL_THEME1_20	F_THEME1_20	SPL_THEME2_20	RPL_THEME2_20	F_THEME2_20	SPL_THEME3_20	RPL_THEME3_20	F_THEME3_20	SPL_THEME4_20	RPL_THEME4_20	F_THEME4_20	SPL_THEMES_20	RPL_THEMES_20	F_TOTAL_20	pre10_lihtc_project_cnt	pre10_lihtc_project_dollars	post10_lihtc_project_cnt	post10_lihtc_project_dollars
01001020100	01	001	020100	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	1809	771	696	297	1809	16.41791	0.3871	36	889	4.049494	0.1790	127	598	21.23746	0.20770	47	98	47.95918	0.5767	174	696	25.00000	0.18790	196	1242	15.780998	0.6093	0	186	1759	10.574190	0.3790	222	12.271973	0.4876	0	445	24.59923	0.5473	0	298	1335	22.32210	0.8454	1	27	545	4.954128	0.09275	0	36	1705	2.1114370	0.59040	385	1809	21.282477	0.4524	0	771	0	0.0000000	0.1224	92	11.9325551	0.8005	1	0	696	0.0000000	0.1238	50	696	7.183908	0.6134	0	1809	0.364	1.74230	0.28200	0	2.56345	0.5296	1	0.4524	0.4482	0	2.0241	0.2519	1	6.78225	0.3278	2	1941	710	693	352	1941	18.13498	0.4630	0	18	852	2.112676	0.15070	81	507	15.976331	0.26320	0	63	186	33.87097	0.2913	0	144	693	20.77922	0.2230	187	1309	14.285714	0.6928	187	1941	9.634209	0.6617	0	295	15.19835	0.4601	0	415	21.38073	0.4681	0	391	1526	25.62254	0.9011	1	58	555	10.45045	0.3451	0	0	1843	0.0000000	0.09479	437	1941	22.51417	0.3902	0	710	0	0.0000000	0.1079	88	12.3943662	0.8263	1	0	693	0.0000000	0.09796	10	693	1.443001	0.1643	0	1941	0.000000	0.1831	0	2.19120	0.4084	0	2.26919	0.3503	1	0.3902	0.3869	0	1.37956	0.07216	1	6.23015	0.2314	2	NA	NA	NA	NA
01001020200	01	001	020200	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	2020	816	730	495	1992	24.84940	0.5954	68	834	8.153477	0.5754	49	439	11.16173	0.02067	105	291	36.08247	0.3019	154	730	21.09589	0.09312	339	1265	26.798419	0.8392	1	313	2012	15.556660	0.6000	204	10.099010	0.3419	0	597	29.55446	0.8192	1	359	1515	23.69637	0.8791	1	132	456	28.947368	0.83510	1	15	1890	0.7936508	0.40130	1243	2020	61.534653	0.7781	1	816	0	0.0000000	0.1224	34	4.1666667	0.6664	0	13	730	1.7808219	0.5406	115	730	15.753425	0.8382	1	2020	0.364	2.70312	0.56650	1	3.27660	0.8614	3	0.7781	0.7709	1	2.5316	0.5047	1	9.28942	0.6832	6	1757	720	573	384	1511	25.41363	0.6427	0	29	717	4.044630	0.41320	33	392	8.418367	0.03542	0	116	181	64.08840	0.9086	1	149	573	26.00349	0.4041	139	1313	10.586443	0.5601	91	1533	5.936073	0.4343	0	284	16.16392	0.5169	0	325	18.49744	0.2851	0	164	1208	13.57616	0.4127	0	42	359	11.69916	0.3998	0	0	1651	0.0000000	0.09479	1116	1757	63.51736	0.7591	1	720	3	0.4166667	0.2470	5	0.6944444	0.5106	0	9	573	1.5706806	0.46880	57	573	9.947644	0.7317	212	1757	12.066022	0.9549	1	2.45440	0.4888	0	1.70929	0.1025	0	0.7591	0.7527	1	2.91300	0.68620	1	7.83579	0.4802	2	NA	NA	NA	NA
01001020300	01	001	020300	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	3543	1403	1287	656	3533	18.56779	0.4443	93	1552	5.992268	0.3724	273	957	28.52665	0.45780	178	330	53.93939	0.7152	451	1287	35.04274	0.49930	346	2260	15.309734	0.5950	0	252	3102	8.123791	0.2596	487	13.745413	0.5868	0	998	28.16822	0.7606	1	371	2224	16.68165	0.6266	0	126	913	13.800657	0.46350	0	0	3365	0.0000000	0.09298	637	3543	17.979114	0.4049	0	1403	10	0.7127584	0.3015	2	0.1425517	0.4407	0	0	1287	0.0000000	0.1238	101	1287	7.847708	0.6443	0	3543	0.364	2.17060	0.41010	0	2.53048	0.5116	1	0.4049	0.4011	0	1.8743	0.1942	0	6.98028	0.3576	1	3694	1464	1351	842	3694	22.79372	0.5833	0	53	1994	2.657974	0.22050	117	967	12.099276	0.11370	0	147	384	38.28125	0.3856	0	264	1351	19.54108	0.1827	317	2477	12.797739	0.6460	127	3673	3.457664	0.2308	0	464	12.56091	0.3088	0	929	25.14889	0.7080	0	473	2744	17.23761	0.6211	0	263	975	26.97436	0.8234	1	128	3586	3.5694367	0.70770	1331	3694	36.03140	0.5515	0	1464	26	1.7759563	0.3675	14	0.9562842	0.5389	0	35	1351	2.5906736	0.60550	42	1351	3.108808	0.3415	0	3694	0.000000	0.1831	0	1.86330	0.3063	0	3.16900	0.8380	1	0.5515	0.5468	0	2.03650	0.26830	0	7.62030	0.4460	1	2	216593	NA	NA
01001020400	01	001	020400	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	4840	1957	1839	501	4840	10.35124	0.2177	101	2129	4.744011	0.2447	310	1549	20.01291	0.17080	89	290	30.68966	0.2044	399	1839	21.69657	0.10540	274	3280	8.353658	0.3205	0	399	4293	9.294200	0.3171	955	19.731405	0.8643	1	1195	24.69008	0.5530	0	625	3328	18.78005	0.7233	0	152	1374	11.062591	0.34710	0	10	4537	0.2204100	0.22560	297	4840	6.136364	0.1647	0	1957	33	1.6862545	0.3843	25	1.2774655	0.5516	0	14	1839	0.7612833	0.3564	19	1839	1.033170	0.1127	0	4840	0.364	1.20540	0.13470	0	2.71330	0.6129	1	0.1647	0.1632	0	1.7690	0.1591	0	5.85240	0.1954	1	3539	1741	1636	503	3539	14.21305	0.3472	0	39	1658	2.352232	0.17990	219	1290	16.976744	0.30880	0	74	346	21.38728	0.1037	0	293	1636	17.90954	0.1333	173	2775	6.234234	0.3351	169	3529	4.788892	0.3448	0	969	27.38062	0.9225	1	510	14.41085	0.1208	0	670	3019	22.19278	0.8194	1	148	1137	13.01671	0.4541	0	89	3409	2.6107363	0.64690	454	3539	12.82848	0.2364	0	1741	143	8.2136703	0.6028	0	0.0000000	0.2186	0	10	1636	0.6112469	0.28340	72	1636	4.400978	0.4538	0	3539	0.000000	0.1831	0	1.34030	0.1575	0	2.96370	0.7496	2	0.2364	0.2344	0	1.74170	0.16270	0	6.28210	0.2389	2	NA	NA	NA	NA
01001020500	01	001	020500	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	9938	3969	3741	1096	9938	11.02838	0.2364	188	4937	3.807981	0.1577	426	2406	17.70574	0.11050	528	1335	39.55056	0.3753	954	3741	25.50120	0.20140	293	5983	4.897209	0.1655	0	740	10110	7.319486	0.2211	837	8.422218	0.2408	0	3012	30.30791	0.8455	1	759	7155	10.60797	0.2668	0	476	2529	18.821669	0.63540	0	78	9297	0.8389803	0.41110	1970	9938	19.822902	0.4330	0	3969	306	7.7097506	0.6153	0	0.0000000	0.2198	0	7	3741	0.1871157	0.2535	223	3741	5.960973	0.5483	0	9938	0.364	0.98210	0.08468	0	2.39960	0.4381	1	0.4330	0.4290	0	2.0009	0.2430	0	5.81560	0.1905	1	10674	4504	4424	1626	10509	15.47245	0.3851	0	81	5048	1.604596	0.09431	321	2299	13.962592	0.17970	0	711	2125	33.45882	0.2836	0	1032	4424	23.32731	0.3109	531	6816	7.790493	0.4251	301	10046	2.996217	0.1894	0	1613	15.11149	0.4553	0	2765	25.90407	0.7494	0	1124	7281	15.43744	0.5253	0	342	2912	11.74451	0.4019	0	52	9920	0.5241935	0.35230	2603	10674	24.38636	0.4160	0	4504	703	15.6083481	0.7378	29	0.6438721	0.5037	0	37	4424	0.8363472	0.33420	207	4424	4.679023	0.4754	176	10674	1.648866	0.7598	1	1.40481	0.1743	0	2.48420	0.4802	0	0.4160	0.4125	0	2.81090	0.63730	1	7.11591	0.3654	1	5	2250459	NA	NA
01001020600	01	001	020600	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	3402	1456	1308	735	3402	21.60494	0.5199	134	1720	7.790698	0.5436	242	1032	23.44961	0.28010	62	276	22.46377	0.1035	304	1308	23.24159	0.14070	301	2151	13.993491	0.5510	0	355	3445	10.304790	0.3656	386	11.346267	0.4232	0	931	27.36626	0.7200	0	440	2439	18.04018	0.6912	0	143	924	15.476190	0.52900	0	4	3254	0.1229256	0.19840	723	3402	21.252205	0.4519	0	1456	18	1.2362637	0.3507	433	29.7390110	0.9468	1	16	1308	1.2232416	0.4493	28	1308	2.140673	0.2298	0	3402	0.364	2.12080	0.39510	0	2.56180	0.5288	0	0.4519	0.4477	0	2.3406	0.4048	1	7.47510	0.4314	1	3536	1464	1330	1279	3523	36.30429	0.8215	1	34	1223	2.780049	0.23780	321	1111	28.892889	0.75870	1	67	219	30.59361	0.2305	0	388	1330	29.17293	0.5075	306	2380	12.857143	0.6480	415	3496	11.870709	0.7535	1	547	15.46946	0.4760	0	982	27.77149	0.8327	1	729	2514	28.99761	0.9488	1	95	880	10.79545	0.3601	0	0	3394	0.0000000	0.09479	985	3536	27.85633	0.4608	0	1464	0	0.0000000	0.1079	364	24.8633880	0.9300	1	0	1330	0.0000000	0.09796	17	1330	1.278196	0.1463	0	3536	0.000000	0.1831	0	2.96830	0.6434	2	2.71239	0.6156	2	0.4608	0.4569	0	1.46526	0.08976	1	7.60675	0.4440	5	NA	NA	NA	NA

Now we need to check our data set to see if there are any 0 counts for our pre10 LIHTC projects. We can see there are none and only NA values:

Code

# Check for 0 counts:
svi_divisional_lihtc20  %>% filter(pre10_lihtc_project_cnt == 0)

# A tibble: 0 × 225
# ℹ 225 variables: GEOID_2010_trt <chr>, FIPS_st <chr>, FIPS_county <chr>,
#   FIPS_tract <chr>, state <chr>, state_name <chr>, county <chr>,
#   region_number <dbl>, region <chr>, division_number <dbl>, division <chr>,
#   E_TOTPOP_10 <dbl>, E_HU_10 <dbl>, E_HH_10 <dbl>, E_POV150_10 <dbl>,
#   ET_POVSTATUS_10 <dbl>, EP_POV150_10 <dbl>, EPL_POV150_10 <dbl>,
#   F_POV150_10 <dbl>, E_UNEMP_10 <dbl>, ET_EMPSTATUS_10 <dbl>,
#   EP_UNEMP_10 <dbl>, EPL_UNEMP_10 <dbl>, F_UNEMP_10 <dbl>, …

Code

# Check for null counts:
svi_divisional_lihtc20  %>% filter(is.na(pre10_lihtc_project_cnt)) %>% head(5) %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID_2010_trt	FIPS_st	FIPS_county	FIPS_tract	state	state_name	county	region_number	region	division_number	division	E_TOTPOP_10	E_HU_10	E_HH_10	E_POV150_10	ET_POVSTATUS_10	EP_POV150_10	EPL_POV150_10	F_POV150_10	E_UNEMP_10	ET_EMPSTATUS_10	EP_UNEMP_10	EPL_UNEMP_10	F_UNEMP_10	E_HBURD_OWN_10	ET_HOUSINGCOST_OWN_10	EP_HBURD_OWN_10	EPL_HBURD_OWN_10	F_HBURD_OWN_10	E_HBURD_RENT_10	ET_HOUSINGCOST_RENT_10	EP_HBURD_RENT_10	EPL_HBURD_RENT_10	F_HBURD_RENT_10	E_HBURD_10	ET_HOUSINGCOST_10	EP_HBURD_10	EPL_HBURD_10	F_HBURD_10	E_NOHSDP_10	ET_EDSTATUS_10	EP_NOHSDP_10	EPL_NOHSDP_10	F_NOHSDP_10	E_UNINSUR_12	ET_INSURSTATUS_12	EP_UNINSUR_12	EPL_UNINSUR_12	F_UNINSUR_12	E_AGE65_10	EP_AGE65_10	EPL_AGE65_10	F_AGE65_10	E_AGE17_10	EP_AGE17_10	EPL_AGE17_10	F_AGE17_10	E_DISABL_12	ET_DISABLSTATUS_12	EP_DISABL_12	EPL_DISABL_12	F_DISABL_12	E_SNGPNT_10	ET_FAMILIES_10	EP_SNGPNT_10	EPL_SNGPNT_10	F_SNGPNT_10	E_LIMENG_10	ET_POPAGE5UP_10	EP_LIMENG_10	EPL_LIMENG_10	F_LIMENG_10	E_MINRTY_10	ET_POPETHRACE_10	EP_MINRTY_10	EPL_MINRTY_10	F_MINRTY_10	E_STRHU_10	E_MUNIT_10	EP_MUNIT_10	EPL_MUNIT_10	F_MUNIT_10	E_MOBILE_10	EP_MOBILE_10	EPL_MOBILE_10	E_CROWD_10	ET_OCCUPANTS_10	EP_CROWD_10	EPL_CROWD_10	F_CROWD_10	E_NOVEH_10	ET_KNOWNVEH_10	EP_NOVEH_10	EPL_NOVEH_10	F_NOVEH_10	E_GROUPQ_10	ET_HHTYPE_10	EP_GROUPQ_10	EPL_GROUPQ_10	F_GROUPQ_10	SPL_THEME1_10	RPL_THEME1_10	F_THEME1_10	SPL_THEME2_10	RPL_THEME2_10	F_THEME2_10	SPL_THEME3_10	RPL_THEME3_10	F_THEME3_10	SPL_THEME4_10	RPL_THEME4_10	F_THEME4_10	SPL_THEMES_10	RPL_THEMES_10	F_TOTAL_10	E_TOTPOP_20	E_HU_20	E_HH_20	E_POV150_20	ET_POVSTATUS_20	EP_POV150_20	EPL_POV150_20	F_POV150_20	E_UNEMP_20	ET_EMPSTATUS_20	EP_UNEMP_20	EPL_UNEMP_20	F_UNEMP_20	E_HBURD_OWN_20	ET_HOUSINGCOST_OWN_20	EP_HBURD_OWN_20	EPL_HBURD_OWN_20	F_HBURD_OWN_20	E_HBURD_RENT_20	ET_HOUSINGCOST_RENT_20	EP_HBURD_RENT_20	EPL_HBURD_RENT_20	F_HBURD_RENT_20	E_HBURD_20	ET_HOUSINGCOST_20	EP_HBURD_20	EPL_HBURD_20	F_HBURD_20	E_NOHSDP_20	ET_EDSTATUS_20	EP_NOHSDP_20	EPL_NOHSDP_20	F_NOHSDP_20	E_UNINSUR_20	ET_INSURSTATUS_20	EP_UNINSUR_20	EPL_UNINSUR_20	F_UNINSUR_20	E_AGE65_20	EP_AGE65_20	EPL_AGE65_20	E_AGE17_20	EP_AGE17_20	EPL_AGE17_20	F_AGE17_20	E_DISABL_20	ET_DISABLSTATUS_20	EP_DISABL_20	EPL_DISABL_20	E_SNGPNT_20	ET_FAMILIES_20	EP_SNGPNT_20	EPL_SNGPNT_20	F_SNGPNT_20	E_LIMENG_20	ET_POPAGE5UP_20	EP_LIMENG_20	EPL_LIMENG_20	F_LIMENG_20	E_MINRTY_20	ET_POPETHRACE_20	EP_MINRTY_20	EPL_MINRTY_20	F_MINRTY_20	E_STRHU_20	E_MUNIT_20	EP_MUNIT_20	EPL_MUNIT_20	F_MUNIT_20	E_MOBILE_20	EP_MOBILE_20	EPL_MOBILE_20	E_CROWD_20	ET_OCCUPANTS_20	EP_CROWD_20	EPL_CROWD_20	F_CROWD_20	E_NOVEH_20	ET_KNOWNVEH_20	EP_NOVEH_20	EPL_NOVEH_20	F_NOVEH_20	E_GROUPQ_20	ET_HHTYPE_20	EP_GROUPQ_20	EPL_GROUPQ_20	SPL_THEME1_20	RPL_THEME1_20	F_THEME1_20	SPL_THEME2_20	RPL_THEME2_20	F_THEME2_20	SPL_THEME3_20	RPL_THEME3_20	F_THEME3_20	SPL_THEME4_20	RPL_THEME4_20	F_THEME4_20	SPL_THEMES_20	RPL_THEMES_20	F_TOTAL_20	pre10_lihtc_project_cnt	pre10_lihtc_project_dollars	post10_lihtc_project_cnt	post10_lihtc_project_dollars
34001000100	34	001	000100	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2907	1088	983	1127	2907	38.76849	0.8482	1	144	1433	10.048849	0.7544	1	280	435	64.36782	0.9529	1	204	548	37.22628	0.2998	0	484	983	49.23703	0.7813	1	468	1759	26.60603	0.8634	1	532	2543	20.92017	0.8978	1	250	8.599931	0.1777	0	944	32.47334	0.94170	1	186	1851	10.04862	0.2706	0	266	678	39.233038	0.8981	1	177	2611	6.779012	0.7778	1	1928	2907	66.32267	0.7743	1	1088	113	10.386029	0.6229	0	9	0.8272059	0.7223	80	983	8.138352	0.8657	1	265	983	26.95829	0.7354	0	0	2907	0.000000	0.3512	0	4.1451	0.8935	5	3.06590	0.7944	3	0.7743	0.7667	1	3.2975	0.8414	1	11.28280	0.8862	10	2157	941	784	1182	2157	54.79833	0.9571	1	242	1058	22.873346	0.9922	1	215	342	62.86550	0.9780	1	316	442	71.49321	0.9481	1	531	784	67.72959	0.9893	1	396	1274	31.08320	0.9497	1	266	2157	12.33194	0.9041	1	185	8.576727	0.09430	552	25.59110	0.8128	1	297	1605	18.504673	0.74880	83	510	16.27451	0.6090	0	251	2020	12.42574	0.8710	1	1852	2157	85.85999	0.8476	1	941	118	12.5398512	0.6385	0	0	0.0000000	0.3216	67	784	8.545918	0.8657	1	212	784	27.04082	0.7502	1	0	2157	0.0000000	0.1517	4.7924	0.9850	5	3.13590	0.8217	2	0.8476	0.8400	1	2.7277	0.6085	2	11.50360	0.9104	10	NA	NA	NA	NA
34001000200	34	001	000200	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3189	2217	1473	519	3189	16.27469	0.4806	0	109	1558	6.996149	0.5179	0	573	955	60.00000	0.9323	1	199	518	38.41699	0.3261	0	772	1473	52.41005	0.8418	1	405	2579	15.70376	0.6491	0	484	3547	13.64533	0.7154	0	847	26.560050	0.9629	1	436	13.67200	0.08181	0	608	3005	20.23295	0.8466	1	42	857	4.900817	0.1204	0	422	3072	13.736979	0.8799	1	1792	3189	56.19316	0.7390	0	2217	901	40.640505	0.8693	1	0	0.0000000	0.3251	48	1473	3.258656	0.7064	0	250	1473	16.97217	0.6444	0	0	3189	0.000000	0.3512	0	3.2048	0.6963	1	2.89161	0.7231	3	0.7390	0.7317	0	2.8964	0.6887	1	9.73181	0.7340	5	3510	2046	1353	1021	3510	29.08832	0.7682	1	121	1852	6.533477	0.6717	0	343	696	49.28161	0.9273	1	416	657	63.31811	0.8696	1	759	1353	56.09756	0.9321	1	553	2338	23.65269	0.8871	1	354	3510	10.08547	0.8530	1	643	18.319088	0.60310	1002	28.54701	0.9055	1	450	2508	17.942584	0.72330	237	786	30.15267	0.8539	1	534	3375	15.82222	0.9062	1	2534	3510	72.19373	0.7818	1	2046	906	44.2815249	0.8690	1	0	0.0000000	0.3216	119	1353	8.795270	0.8711	1	324	1353	23.94678	0.7255	0	0	3510	0.0000000	0.1517	4.1121	0.9003	4	3.99200	0.9781	3	0.7818	0.7747	1	2.9389	0.7011	2	11.82480	0.9310	10	NA	NA	NA	NA
34001000300	34	001	000300	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3997	1823	1357	1401	3968	35.30746	0.8164	1	382	2238	17.068811	0.9376	1	176	329	53.49544	0.8855	1	604	1028	58.75486	0.7947	1	780	1357	57.47973	0.9165	1	920	2677	34.36683	0.9346	1	1351	4149	32.56206	0.9811	1	314	7.855892	0.1437	0	937	23.44258	0.55900	0	319	3054	10.44532	0.3000	0	187	782	23.913044	0.7498	0	1080	3671	29.419777	0.9742	1	3357	3997	83.98799	0.8419	1	1823	363	19.912233	0.7535	1	0	0.0000000	0.3251	150	1357	11.053795	0.9136	1	651	1357	47.97347	0.8585	1	0	3997	0.000000	0.3512	0	4.5862	0.9691	5	2.72670	0.6360	1	0.8419	0.8336	1	3.2019	0.8054	3	11.35670	0.8920	10	3801	1640	1226	1857	3801	48.85556	0.9333	1	226	1800	12.555556	0.9267	1	111	280	39.64286	0.8339	1	608	946	64.27061	0.8842	1	719	1226	58.64600	0.9528	1	650	2275	28.57143	0.9337	1	1027	3801	27.01921	0.9914	1	380	9.997369	0.14040	1223	32.17574	0.9607	1	219	2578	8.494957	0.15680	268	909	29.48295	0.8456	1	940	3400	27.64706	0.9728	1	3318	3801	87.29282	0.8579	1	1640	262	15.9756098	0.6917	0	0	0.0000000	0.3216	124	1226	10.114192	0.8955	1	477	1226	38.90701	0.8258	1	0	3801	0.0000000	0.1517	4.7379	0.9829	5	3.07630	0.8013	3	0.8579	0.8501	1	2.8863	0.6781	2	11.55840	0.9150	11	NA	NA	NA	NA
34001000400	34	001	000400	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	2902	2683	1401	1172	2902	40.38594	0.8615	1	190	1389	13.678906	0.8811	1	364	707	51.48515	0.8627	1	507	694	73.05476	0.9503	1	871	1401	62.16988	0.9572	1	481	1981	24.28067	0.8339	1	674	3204	21.03620	0.8998	1	434	14.955203	0.6083	0	596	20.53756	0.33980	0	426	2607	16.34062	0.6886	0	111	652	17.024540	0.6204	0	215	2736	7.858187	0.8008	1	1792	2902	61.75052	0.7584	1	2683	2049	76.369735	0.9401	1	0	0.0000000	0.3251	69	1401	4.925053	0.7847	1	511	1401	36.47395	0.7992	1	72	2902	2.481048	0.8114	1	4.4335	0.9468	5	3.05790	0.7908	1	0.7584	0.7510	1	3.6605	0.9391	4	11.91030	0.9339	11	3178	2264	1390	1508	3176	47.48111	0.9246	1	172	1804	9.534368	0.8460	1	205	468	43.80342	0.8858	1	622	922	67.46204	0.9192	1	827	1390	59.49640	0.9587	1	364	2076	17.53372	0.8013	1	476	3178	14.97797	0.9390	1	483	15.198238	0.41220	539	16.96035	0.2484	0	319	2639	12.087912	0.38790	101	565	17.87611	0.6539	0	583	3022	19.29186	0.9349	1	2186	3178	68.78540	0.7658	1	2264	1609	71.0689046	0.9266	1	15	0.6625442	0.7078	226	1390	16.258993	0.9567	1	599	1390	43.09353	0.8474	1	20	3178	0.6293266	0.6292	4.4696	0.9558	5	2.63730	0.5864	1	0.7658	0.7588	1	4.0677	0.9762	3	11.94040	0.9387	10	NA	NA	NA	NA
34001000500	34	001	000500	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3483	1241	1027	1938	3483	55.64169	0.9533	1	124	1630	7.607362	0.5830	0	227	446	50.89686	0.8549	1	478	581	82.27194	0.9799	1	705	1027	68.64654	0.9863	1	733	2077	35.29129	0.9396	1	727	3258	22.31430	0.9149	1	377	10.824002	0.3081	0	1055	30.28998	0.90140	1	268	2401	11.16202	0.3549	0	209	763	27.391874	0.7940	1	911	3077	29.606760	0.9746	1	3036	3483	87.16624	0.8550	1	1241	52	4.190169	0.4505	0	4	0.3223207	0.6567	113	1027	11.002921	0.9128	1	422	1027	41.09056	0.8250	1	0	3483	0.000000	0.3512	0	4.3771	0.9379	4	3.33300	0.8766	3	0.8550	0.8467	1	3.1962	0.8026	2	11.76130	0.9229	10	3385	1185	945	1682	3364	50.00000	0.9391	1	72	1577	4.565631	0.4586	0	185	468	39.52991	0.8332	1	362	477	75.89099	0.9703	1	547	945	57.88360	0.9477	1	592	1983	29.85376	0.9422	1	738	3385	21.80207	0.9817	1	240	7.090103	0.05988	1129	33.35303	0.9689	1	135	2256	5.984043	0.04817	110	717	15.34170	0.5822	0	721	3076	23.43953	0.9569	1	3029	3385	89.48301	0.8727	1	1185	9	0.7594937	0.2382	0	0	0.0000000	0.3216	103	945	10.899471	0.9072	1	263	945	27.83069	0.7560	1	0	3385	0.0000000	0.1517	4.2693	0.9283	4	2.61605	0.5709	2	0.8727	0.8648	1	2.3747	0.4357	2	10.13275	0.7921	9	NA	NA	NA	NA

Code

# Check for 0 counts:
svi_national_lihtc20  %>% filter(pre10_lihtc_project_cnt == 0)

# A tibble: 0 × 225
# ℹ 225 variables: GEOID_2010_trt <chr>, FIPS_st <chr>, FIPS_county <chr>,
#   FIPS_tract <chr>, state <chr>, state_name <chr>, county <chr>,
#   region_number <dbl>, region <chr>, division_number <dbl>, division <chr>,
#   E_TOTPOP_10 <dbl>, E_HU_10 <dbl>, E_HH_10 <dbl>, E_POV150_10 <dbl>,
#   ET_POVSTATUS_10 <dbl>, EP_POV150_10 <dbl>, EPL_POV150_10 <dbl>,
#   F_POV150_10 <dbl>, E_UNEMP_10 <dbl>, ET_EMPSTATUS_10 <dbl>,
#   EP_UNEMP_10 <dbl>, EPL_UNEMP_10 <dbl>, F_UNEMP_10 <dbl>, …

Code

# Check for null counts:
svi_national_lihtc20  %>% filter(is.na(pre10_lihtc_project_cnt)) %>% head(5) %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID_2010_trt	FIPS_st	FIPS_county	FIPS_tract	state	state_name	county	region_number	region	division_number	division	E_TOTPOP_10	E_HU_10	E_HH_10	E_POV150_10	ET_POVSTATUS_10	EP_POV150_10	EPL_POV150_10	E_UNEMP_10	ET_EMPSTATUS_10	EP_UNEMP_10	EPL_UNEMP_10	E_HBURD_OWN_10	ET_HOUSINGCOST_OWN_10	EP_HBURD_OWN_10	EPL_HBURD_OWN_10	E_HBURD_RENT_10	ET_HOUSINGCOST_RENT_10	EP_HBURD_RENT_10	EPL_HBURD_RENT_10	E_HBURD_10	ET_HOUSINGCOST_10	EP_HBURD_10	EPL_HBURD_10	E_NOHSDP_10	ET_EDSTATUS_10	EP_NOHSDP_10	EPL_NOHSDP_10	F_NOHSDP_10	E_UNINSUR_12	ET_INSURSTATUS_12	EP_UNINSUR_12	EPL_UNINSUR_12	E_AGE65_10	EP_AGE65_10	EPL_AGE65_10	F_AGE65_10	E_AGE17_10	EP_AGE17_10	EPL_AGE17_10	F_AGE17_10	E_DISABL_12	ET_DISABLSTATUS_12	EP_DISABL_12	EPL_DISABL_12	F_DISABL_12	E_SNGPNT_10	ET_FAMILIES_10	EP_SNGPNT_10	EPL_SNGPNT_10	F_SNGPNT_10	E_LIMENG_10	ET_POPAGE5UP_10	EP_LIMENG_10	EPL_LIMENG_10	E_MINRTY_10	ET_POPETHRACE_10	EP_MINRTY_10	EPL_MINRTY_10	F_MINRTY_10	E_STRHU_10	E_MUNIT_10	EP_MUNIT_10	EPL_MUNIT_10	E_MOBILE_10	EP_MOBILE_10	EPL_MOBILE_10	F_MOBILE_10	E_CROWD_10	ET_OCCUPANTS_10	EP_CROWD_10	EPL_CROWD_10	E_NOVEH_10	ET_KNOWNVEH_10	EP_NOVEH_10	EPL_NOVEH_10	F_NOVEH_10	ET_HHTYPE_10	EPL_GROUPQ_10	SPL_THEME1_10	RPL_THEME1_10	F_THEME1_10	SPL_THEME2_10	RPL_THEME2_10	F_THEME2_10	SPL_THEME3_10	RPL_THEME3_10	F_THEME3_10	SPL_THEME4_10	RPL_THEME4_10	F_THEME4_10	SPL_THEMES_10	RPL_THEMES_10	F_TOTAL_10	E_TOTPOP_20	E_HU_20	E_HH_20	E_POV150_20	ET_POVSTATUS_20	EP_POV150_20	EPL_POV150_20	F_POV150_20	E_UNEMP_20	ET_EMPSTATUS_20	EP_UNEMP_20	EPL_UNEMP_20	F_UNEMP_20	E_HBURD_OWN_20	ET_HOUSINGCOST_OWN_20	EP_HBURD_OWN_20	EPL_HBURD_OWN_20	F_HBURD_OWN_20	E_HBURD_RENT_20	ET_HOUSINGCOST_RENT_20	EP_HBURD_RENT_20	EPL_HBURD_RENT_20	F_HBURD_RENT_20	E_HBURD_20	ET_HOUSINGCOST_20	EP_HBURD_20	EPL_HBURD_20	E_NOHSDP_20	ET_EDSTATUS_20	EP_NOHSDP_20	EPL_NOHSDP_20	F_NOHSDP_20	E_UNINSUR_20	ET_INSURSTATUS_20	EP_UNINSUR_20	EPL_UNINSUR_20	F_UNINSUR_20	E_AGE65_20	EP_AGE65_20	EPL_AGE65_20	F_AGE65_20	E_AGE17_20	EP_AGE17_20	EPL_AGE17_20	F_AGE17_20	E_DISABL_20	ET_DISABLSTATUS_20	EP_DISABL_20	EPL_DISABL_20	F_DISABL_20	E_SNGPNT_20	ET_FAMILIES_20	EP_SNGPNT_20	EPL_SNGPNT_20	E_LIMENG_20	ET_POPAGE5UP_20	EP_LIMENG_20	EPL_LIMENG_20	E_MINRTY_20	ET_POPETHRACE_20	EP_MINRTY_20	EPL_MINRTY_20	F_MINRTY_20	E_STRHU_20	E_MUNIT_20	EP_MUNIT_20	EPL_MUNIT_20	E_MOBILE_20	EP_MOBILE_20	EPL_MOBILE_20	F_MOBILE_20	E_CROWD_20	ET_OCCUPANTS_20	EP_CROWD_20	EPL_CROWD_20	F_CROWD_20	E_NOVEH_20	ET_KNOWNVEH_20	EP_NOVEH_20	EPL_NOVEH_20	E_GROUPQ_20	ET_HHTYPE_20	EP_GROUPQ_20	EPL_GROUPQ_20	F_GROUPQ_20	SPL_THEME1_20	RPL_THEME1_20	F_THEME1_20	SPL_THEME2_20	RPL_THEME2_20	F_THEME2_20	SPL_THEME3_20	RPL_THEME3_20	F_THEME3_20	SPL_THEME4_20	RPL_THEME4_20	F_THEME4_20	SPL_THEMES_20	RPL_THEMES_20	F_TOTAL_20	pre10_lihtc_project_cnt	pre10_lihtc_project_dollars	post10_lihtc_project_cnt	post10_lihtc_project_dollars
01001020100	01	001	020100	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	1809	771	696	297	1809	16.41791	0.3871	36	889	4.049494	0.17900	127	598	21.23746	0.20770	47	98	47.95918	0.5767	174	696	25.00000	0.18790	196	1242	15.780998	0.6093	0	186	1759	10.57419	0.3790	222	12.27197	0.4876	0	445	24.59923	0.5473	0	298	1335	22.32210	0.8454	1	27	545	4.954128	0.09275	0	36	1705	2.1114370	0.59040	385	1809	21.282477	0.4524	0	771	0	0.0000000	0.1224	92	11.932555	0.8005	1	0	696	0.0000000	0.1238	50	696	7.183908	0.6134	0	1809	0.364	1.74230	0.2820	0	2.56345	0.5296	1	0.4524	0.4482	0	2.0241	0.2519	1	6.78225	0.3278	2	1941	710	693	352	1941	18.13498	0.4630	0	18	852	2.112676	0.1507	0	81	507	15.976331	0.26320	0	63	186	33.87097	0.2913	0	144	693	20.77922	0.2230	187	1309	14.285714	0.6928	0	187	1941	9.634209	0.6617	0	295	15.198351	0.4601	0	415	21.38073	0.4681	0	391	1526	25.62254	0.9011	1	58	555	10.45045	0.3451	0	1843	0.000000	0.09479	437	1941	22.51417	0.3902	0	710	0	0.0000000	0.1079	88	12.3943662	0.8263	1	0	693	0.0000000	0.09796	0	10	693	1.443001	0.1643	0	1941	0.000000	0.1831	0	2.1912	0.4084	0	2.26919	0.3503	1	0.3902	0.3869	0	1.37956	0.07216	1	6.23015	0.2314	2	NA	NA	NA	NA
01001020200	01	001	020200	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	2020	816	730	495	1992	24.84940	0.5954	68	834	8.153477	0.57540	49	439	11.16173	0.02067	105	291	36.08247	0.3019	154	730	21.09589	0.09312	339	1265	26.798419	0.8392	1	313	2012	15.55666	0.6000	204	10.09901	0.3419	0	597	29.55446	0.8192	1	359	1515	23.69637	0.8791	1	132	456	28.947368	0.83510	1	15	1890	0.7936508	0.40130	1243	2020	61.534653	0.7781	1	816	0	0.0000000	0.1224	34	4.166667	0.6664	0	13	730	1.7808219	0.5406	115	730	15.753425	0.8382	1	2020	0.364	2.70312	0.5665	1	3.27660	0.8614	3	0.7781	0.7709	1	2.5316	0.5047	1	9.28942	0.6832	6	1757	720	573	384	1511	25.41363	0.6427	0	29	717	4.044630	0.4132	0	33	392	8.418367	0.03542	0	116	181	64.08840	0.9086	1	149	573	26.00349	0.4041	139	1313	10.586443	0.5601	0	91	1533	5.936073	0.4343	0	284	16.163916	0.5169	0	325	18.49744	0.2851	0	164	1208	13.57616	0.4127	0	42	359	11.69916	0.3998	0	1651	0.000000	0.09479	1116	1757	63.51736	0.7591	1	720	3	0.4166667	0.2470	5	0.6944444	0.5106	0	9	573	1.5706806	0.46880	0	57	573	9.947644	0.7317	212	1757	12.066022	0.9549	1	2.4544	0.4888	0	1.70929	0.1025	0	0.7591	0.7527	1	2.91300	0.68620	1	7.83579	0.4802	2	NA	NA	NA	NA
01001020400	01	001	020400	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	4840	1957	1839	501	4840	10.35124	0.2177	101	2129	4.744011	0.24470	310	1549	20.01291	0.17080	89	290	30.68966	0.2044	399	1839	21.69657	0.10540	274	3280	8.353658	0.3205	0	399	4293	9.29420	0.3171	955	19.73140	0.8643	1	1195	24.69008	0.5530	0	625	3328	18.78005	0.7233	0	152	1374	11.062591	0.34710	0	10	4537	0.2204100	0.22560	297	4840	6.136364	0.1647	0	1957	33	1.6862545	0.3843	25	1.277465	0.5516	0	14	1839	0.7612833	0.3564	19	1839	1.033170	0.1127	0	4840	0.364	1.20540	0.1347	0	2.71330	0.6129	1	0.1647	0.1632	0	1.7690	0.1591	0	5.85240	0.1954	1	3539	1741	1636	503	3539	14.21305	0.3472	0	39	1658	2.352232	0.1799	0	219	1290	16.976744	0.30880	0	74	346	21.38728	0.1037	0	293	1636	17.90954	0.1333	173	2775	6.234234	0.3351	0	169	3529	4.788892	0.3448	0	969	27.380616	0.9225	1	510	14.41085	0.1208	0	670	3019	22.19278	0.8194	1	148	1137	13.01671	0.4541	89	3409	2.610736	0.64690	454	3539	12.82848	0.2364	0	1741	143	8.2136703	0.6028	0	0.0000000	0.2186	0	10	1636	0.6112469	0.28340	0	72	1636	4.400978	0.4538	0	3539	0.000000	0.1831	0	1.3403	0.1575	0	2.96370	0.7496	2	0.2364	0.2344	0	1.74170	0.16270	0	6.28210	0.2389	2	NA	NA	NA	NA
01001020600	01	001	020600	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	3402	1456	1308	735	3402	21.60494	0.5199	134	1720	7.790698	0.54360	242	1032	23.44961	0.28010	62	276	22.46377	0.1035	304	1308	23.24159	0.14070	301	2151	13.993491	0.5510	0	355	3445	10.30479	0.3656	386	11.34627	0.4232	0	931	27.36626	0.7200	0	440	2439	18.04018	0.6912	0	143	924	15.476190	0.52900	0	4	3254	0.1229256	0.19840	723	3402	21.252205	0.4519	0	1456	18	1.2362637	0.3507	433	29.739011	0.9468	1	16	1308	1.2232416	0.4493	28	1308	2.140673	0.2298	0	3402	0.364	2.12080	0.3951	0	2.56180	0.5288	0	0.4519	0.4477	0	2.3406	0.4048	1	7.47510	0.4314	1	3536	1464	1330	1279	3523	36.30429	0.8215	1	34	1223	2.780049	0.2378	0	321	1111	28.892889	0.75870	1	67	219	30.59361	0.2305	0	388	1330	29.17293	0.5075	306	2380	12.857143	0.6480	0	415	3496	11.870709	0.7535	1	547	15.469457	0.4760	0	982	27.77149	0.8327	1	729	2514	28.99761	0.9488	1	95	880	10.79545	0.3601	0	3394	0.000000	0.09479	985	3536	27.85633	0.4608	0	1464	0	0.0000000	0.1079	364	24.8633880	0.9300	1	0	1330	0.0000000	0.09796	0	17	1330	1.278196	0.1463	0	3536	0.000000	0.1831	0	2.9683	0.6434	2	2.71239	0.6156	2	0.4608	0.4569	0	1.46526	0.08976	1	7.60675	0.4440	5	NA	NA	NA	NA
01001020700	01	001	020700	AL	Alabama	Autauga County	3	South Region	6	East South Central Division	2664	1254	1139	710	2664	26.65165	0.6328	29	1310	2.213741	0.05255	134	710	18.87324	0.13890	187	429	43.58974	0.4709	321	1139	28.18262	0.28130	396	1852	21.382289	0.7478	0	345	2878	11.98749	0.4459	389	14.60210	0.6417	0	599	22.48499	0.4007	0	510	2168	23.52399	0.8752	1	228	712	32.022472	0.87120	1	0	2480	0.0000000	0.09298	694	2664	26.051051	0.5138	0	1254	8	0.6379585	0.2931	460	36.682616	0.9714	1	0	1139	0.0000000	0.1238	125	1139	10.974539	0.7477	0	2664	0.364	2.16035	0.4069	0	2.88178	0.6997	2	0.5138	0.5090	0	2.5000	0.4882	1	8.05593	0.5185	3	3562	1313	1248	1370	3528	38.83220	0.8512	1	128	1562	8.194622	0.7935	1	168	844	19.905213	0.44510	0	237	404	58.66337	0.8359	1	405	1248	32.45192	0.6042	396	2211	17.910448	0.7857	1	444	3547	12.517620	0.7758	1	355	9.966311	0.1800	0	954	26.78271	0.7923	1	629	2593	24.25762	0.8730	1	171	797	21.45546	0.7186	0	3211	0.000000	0.09479	1009	3562	28.32678	0.4668	0	1313	14	1.0662605	0.3165	443	33.7395278	0.9663	1	73	1248	5.8493590	0.82110	1	17	1248	1.362180	0.1554	112	3562	3.144301	0.8514	1	3.8104	0.8569	4	2.65869	0.5847	2	0.4668	0.4629	0	3.11070	0.77140	3	10.04659	0.7851	9	NA	NA	NA	NA

We can now filter our data set to only keep the census tracts that have a null (NA) for pre10 projects, indicating there were no projects in the tract. We also only want to keep tracts with a project after 2010:

Code

svi_divisional_lihtc20 <- svi_divisional_lihtc20 %>% 
  filter(is.na(pre10_lihtc_project_cnt)) %>% 
  filter(post10_lihtc_project_cnt >= 1) %>% 
  select(GEOID_2010_trt, pre10_lihtc_project_cnt, pre10_lihtc_project_dollars, post10_lihtc_project_cnt, post10_lihtc_project_dollars)

# View data
svi_divisional_lihtc20 %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID_2010_trt	pre10_lihtc_project_cnt	pre10_lihtc_project_dollars	post10_lihtc_project_cnt	post10_lihtc_project_dollars
34001001500	NA	NA	1	1497998
34001010600	NA	NA	1	1369830
34001011803	NA	NA	1	0
34003002200	NA	NA	1	0
34003007001	NA	NA	1	601714
34003013001	NA	NA	1	307351

Code

svi_national_lihtc20 <- svi_national_lihtc20 %>% 
  filter(is.na(pre10_lihtc_project_cnt)) %>% 
  filter(post10_lihtc_project_cnt >= 1) %>% 
  select(GEOID_2010_trt, pre10_lihtc_project_cnt, pre10_lihtc_project_dollars, post10_lihtc_project_cnt, post10_lihtc_project_dollars)

# View data
svi_national_lihtc20 %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID_2010_trt	pre10_lihtc_project_cnt	pre10_lihtc_project_dollars	post10_lihtc_project_cnt	post10_lihtc_project_dollars
01003010500	NA	NA	1	481325
01003011601	NA	NA	1	887856
01017954600	NA	NA	2	950192
01021060101	NA	NA	1	812048
01039962600	NA	NA	1	434742
01043964900	NA	NA	1	1046201

Now we need to create our final data set:

Code

# Filter SVI divisional data to remove all tracts that had a project in 2010 or before:
svi_divisional_lihtc <-  svi_divisional %>% 
  filter(! GEOID_2010_trt %in% lihtc_projects10$fips2010)

# Merge SVI divisional data with post 2010 project data, create flag for projects (1 for tracts that have LIHTC project, 0 for those that do not):
svi_divisional_lihtc <- left_join(svi_divisional_lihtc, 
                                  svi_divisional_lihtc20, 
                                  join_by("GEOID_2010_trt" == "GEOID_2010_trt")) %>% 
                        mutate(pre10_lihtc_project_cnt = replace_na(pre10_lihtc_project_cnt, 0),
                               post10_lihtc_project_cnt = replace_na(post10_lihtc_project_cnt, 0),
                               pre10_lihtc_project_dollars = replace_na(pre10_lihtc_project_dollars, 0),
                               post10_lihtc_project_dollars = replace_na(post10_lihtc_project_dollars, 0),
                               lihtc_flag = if_else(post10_lihtc_project_cnt >= 1, 1, 0))

# Finally, we want to filter our dataset to only have tracts that are eligible for the LIHTC program and that have SVI data:
svi_divisional_lihtc <- left_join(svi_divisional_lihtc, lihtc_eligible_flag, 
                                  join_by("GEOID_2010_trt" == "GEOID10")) %>%
                        filter(tolower(lihtc_eligibility) == "yes") %>%
                        filter(!is.na(F_TOTAL_10)) %>% 
                        filter(!is.na(F_TOTAL_20)) 


# View data
svi_divisional_lihtc %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID_2010_trt	FIPS_st	FIPS_county	FIPS_tract	state	state_name	county	region_number	region	division_number	division	E_TOTPOP_10	E_HU_10	E_HH_10	E_POV150_10	ET_POVSTATUS_10	EP_POV150_10	EPL_POV150_10	F_POV150_10	E_UNEMP_10	ET_EMPSTATUS_10	EP_UNEMP_10	EPL_UNEMP_10	F_UNEMP_10	E_HBURD_OWN_10	ET_HOUSINGCOST_OWN_10	EP_HBURD_OWN_10	EPL_HBURD_OWN_10	F_HBURD_OWN_10	E_HBURD_RENT_10	ET_HOUSINGCOST_RENT_10	EP_HBURD_RENT_10	EPL_HBURD_RENT_10	F_HBURD_RENT_10	E_HBURD_10	ET_HOUSINGCOST_10	EP_HBURD_10	EPL_HBURD_10	F_HBURD_10	E_NOHSDP_10	ET_EDSTATUS_10	EP_NOHSDP_10	EPL_NOHSDP_10	F_NOHSDP_10	E_UNINSUR_12	ET_INSURSTATUS_12	EP_UNINSUR_12	EPL_UNINSUR_12	F_UNINSUR_12	E_AGE65_10	EP_AGE65_10	EPL_AGE65_10	F_AGE65_10	E_AGE17_10	EP_AGE17_10	EPL_AGE17_10	F_AGE17_10	E_DISABL_12	ET_DISABLSTATUS_12	EP_DISABL_12	EPL_DISABL_12	F_DISABL_12	E_SNGPNT_10	ET_FAMILIES_10	EP_SNGPNT_10	EPL_SNGPNT_10	F_SNGPNT_10	E_LIMENG_10	ET_POPAGE5UP_10	EP_LIMENG_10	EPL_LIMENG_10	F_LIMENG_10	E_MINRTY_10	ET_POPETHRACE_10	EP_MINRTY_10	EPL_MINRTY_10	F_MINRTY_10	E_STRHU_10	E_MUNIT_10	EP_MUNIT_10	EPL_MUNIT_10	F_MUNIT_10	E_MOBILE_10	EP_MOBILE_10	EPL_MOBILE_10	F_MOBILE_10	E_CROWD_10	ET_OCCUPANTS_10	EP_CROWD_10	EPL_CROWD_10	F_CROWD_10	E_NOVEH_10	ET_KNOWNVEH_10	EP_NOVEH_10	EPL_NOVEH_10	F_NOVEH_10	E_GROUPQ_10	ET_HHTYPE_10	EP_GROUPQ_10	EPL_GROUPQ_10	F_GROUPQ_10	SPL_THEME1_10	RPL_THEME1_10	F_THEME1_10	SPL_THEME2_10	RPL_THEME2_10	F_THEME2_10	SPL_THEME3_10	RPL_THEME3_10	F_THEME3_10	SPL_THEME4_10	RPL_THEME4_10	F_THEME4_10	SPL_THEMES_10	RPL_THEMES_10	F_TOTAL_10	E_TOTPOP_20	E_HU_20	E_HH_20	E_POV150_20	ET_POVSTATUS_20	EP_POV150_20	EPL_POV150_20	F_POV150_20	E_UNEMP_20	ET_EMPSTATUS_20	EP_UNEMP_20	EPL_UNEMP_20	F_UNEMP_20	E_HBURD_OWN_20	ET_HOUSINGCOST_OWN_20	EP_HBURD_OWN_20	EPL_HBURD_OWN_20	F_HBURD_OWN_20	E_HBURD_RENT_20	ET_HOUSINGCOST_RENT_20	EP_HBURD_RENT_20	EPL_HBURD_RENT_20	F_HBURD_RENT_20	E_HBURD_20	ET_HOUSINGCOST_20	EP_HBURD_20	EPL_HBURD_20	F_HBURD_20	E_NOHSDP_20	ET_EDSTATUS_20	EP_NOHSDP_20	EPL_NOHSDP_20	F_NOHSDP_20	E_UNINSUR_20	ET_INSURSTATUS_20	EP_UNINSUR_20	EPL_UNINSUR_20	F_UNINSUR_20	E_AGE65_20	EP_AGE65_20	EPL_AGE65_20	F_AGE65_20	E_AGE17_20	EP_AGE17_20	EPL_AGE17_20	F_AGE17_20	E_DISABL_20	ET_DISABLSTATUS_20	EP_DISABL_20	EPL_DISABL_20	F_DISABL_20	E_SNGPNT_20	ET_FAMILIES_20	EP_SNGPNT_20	EPL_SNGPNT_20	F_SNGPNT_20	E_LIMENG_20	ET_POPAGE5UP_20	EP_LIMENG_20	EPL_LIMENG_20	F_LIMENG_20	E_MINRTY_20	ET_POPETHRACE_20	EP_MINRTY_20	EPL_MINRTY_20	F_MINRTY_20	E_STRHU_20	E_MUNIT_20	EP_MUNIT_20	EPL_MUNIT_20	F_MUNIT_20	EPL_MOBILE_20	E_CROWD_20	ET_OCCUPANTS_20	EP_CROWD_20	EPL_CROWD_20	F_CROWD_20	E_NOVEH_20	ET_KNOWNVEH_20	EP_NOVEH_20	EPL_NOVEH_20	F_NOVEH_20	E_GROUPQ_20	ET_HHTYPE_20	EP_GROUPQ_20	EPL_GROUPQ_20	F_GROUPQ_20	SPL_THEME1_20	RPL_THEME1_20	F_THEME1_20	SPL_THEME2_20	RPL_THEME2_20	F_THEME2_20	SPL_THEME3_20	RPL_THEME3_20	F_THEME3_20	SPL_THEME4_20	RPL_THEME4_20	F_THEME4_20	SPL_THEMES_20	RPL_THEMES_20	F_TOTAL_20	post10_lihtc_project_cnt	post10_lihtc_project_dollars	lihtc_flag	lihtc_eligibility
34001001400	34	001	001400	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3736	1893	1503	2135	3736	57.14668	0.9592	1	411	1635	25.137615	0.9866	1	267	401	66.58354	0.9617	1	715	1102	64.88203	0.8844	1	982	1503	65.33599	0.9764	1	511	1696	30.129717	0.90050	1	527	4199	12.5506073	0.672800	0	269	7.200214	0.115100	0	1598	42.77302	0.9935	1	345	2252	15.319716	0.63090	0	787	941	83.63443	0.9990	1	63	3192	1.973684	0.54480	0	3463	3736	92.69272	0.8905	1	1893	427	22.556788	0.7770	1	0	0.000000	0.3251	0	22	1503	1.463739	0.5339	0	705	1503	46.90619	0.85330	1	0	3736	0.000000	0.3512	0	4.495500	0.9585	4	3.283300	0.8640	2	0.8905	0.8818	1	2.84050	0.66710	2	11.509800	0.9048	9	3812	1724	1549	2291	3754	61.028236	0.9760	1	380	1547	24.563672	0.9934	1	117	240	48.75000	0.9237	1	753	1309	57.52483	0.7816	1	870	1549	56.16527	0.9326	1	472	1913	24.673288	0.8987	1	294	3802	7.7327722	0.7558	1	363	9.52256	0.123100	0	1463	38.37880	0.9885	1	508	2339.000	21.718683	0.85640	1	564	948.000	59.49367	0.9910	1	201	3159	6.3627730	0.7613	1	3389	3812.000	88.90346	0.8683	1	1724	571	33.1206497	0.8294	1	0.3216	83	1549	5.358296	0.7754	1	661	1549.000	42.672692	0.8448	1	10	3812	0.2623295	0.4739	0	4.5565	0.9673	5	3.720300	0.9522	4	0.8683	0.8605	1	3.2451	0.81590	3	12.390200	0.9595	13	0	0	0	Yes
34001001500	34	001	001500	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	1074	901	752	656	1074	61.08007	0.9700	1	43	270	15.925926	0.9242	1	30	70	42.85714	0.7276	0	366	682	53.66569	0.6910	0	396	752	52.65957	0.8458	1	266	921	28.881650	0.88860	1	121	1064	11.3721805	0.613100	0	385	35.847300	0.990200	1	129	12.01117	0.0617	0	321	993	32.326284	0.98460	1	62	195	31.79487	0.8408	1	125	1050	11.904762	0.85620	1	965	1074	89.85102	0.8717	1	901	636	70.588235	0.9304	1	0	0.000000	0.3251	0	10	752	1.329787	0.5133	0	626	752	83.24468	0.98880	1	0	1074	0.000000	0.3512	0	4.241700	0.9134	4	3.733500	0.9515	4	0.8717	0.8632	1	3.10880	0.77090	2	11.955700	0.9362	11	1601	976	810	1001	1601	62.523423	0.9797	1	204	563	36.234458	0.9989	1	74	110	67.27273	0.9848	1	224	700	32.00000	0.2097	0	298	810	36.79012	0.6089	0	379	1145	33.100437	0.9610	1	272	1601	16.9893816	0.9572	1	451	28.16989	0.936300	1	251	15.67770	0.1835	0	411	1350.000	30.444444	0.97330	1	196	446.000	43.94619	0.9511	1	220	1532	14.3603133	0.8929	1	1435	1601.000	89.63148	0.8738	1	976	451	46.2090164	0.8742	1	0.3216	24	810	2.962963	0.6412	0	546	810.000	67.407407	0.9401	1	15	1601	0.9369144	0.6832	0	4.5057	0.9617	4	3.937100	0.9752	4	0.8738	0.8659	1	3.4603	0.87740	2	12.776900	0.9705	11	1	1497998	1	Yes
34001002400	34	001	002400	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	3129	1759	1375	1916	3129	61.23362	0.9705	1	205	1075	19.069767	0.9574	1	28	60	46.66667	0.7987	1	670	1315	50.95057	0.6297	0	698	1375	50.76364	0.8102	1	632	2059	30.694512	0.90660	1	461	2365	19.4926004	0.873700	1	539	17.225951	0.744100	0	850	27.16523	0.7907	1	575	1736	33.122120	0.98650	1	237	594	39.89899	0.9035	1	312	2663	11.716110	0.85490	1	2357	3129	75.32758	0.8038	1	1759	1091	62.023877	0.9176	1	29	1.648664	0.7742	1	57	1375	4.145454	0.7529	1	696	1375	50.61818	0.87140	1	209	3129	6.679450	0.9003	1	4.518400	0.9608	5	4.279700	0.9831	4	0.8038	0.7960	1	4.21640	0.98320	5	13.818300	0.9835	15	2614	1726	1217	1579	2612	60.451761	0.9744	1	290	1171	24.765158	0.9939	1	69	127	54.33071	0.9521	1	538	1090	49.35780	0.5970	0	607	1217	49.87675	0.8624	1	697	1998	34.884885	0.9695	1	551	2614	21.0788064	0.9797	1	516	19.73986	0.679400	0	503	19.24254	0.3999	0	576	2111.000	27.285647	0.95060	1	257	567.000	45.32628	0.9571	1	556	2368	23.4797297	0.9570	1	2029	2614.000	77.62050	0.8058	1	1726	1166	67.5550406	0.9204	1	0.3216	115	1217	9.449466	0.8840	1	673	1217.000	55.299918	0.8978	1	223	2614	8.5309870	0.9307	1	4.7799	0.9845	5	3.944000	0.9756	3	0.8058	0.7985	1	3.9545	0.96510	4	13.484200	0.9845	13	0	0	0	Yes
34003015400	34	003	015400	NJ	New Jersey	Bergen County	1	Northeast Region	2	Middle Atlantic Division	5086	2258	2100	1485	5063	29.33044	0.7447	0	195	2873	6.787330	0.4938	0	223	478	46.65272	0.7984	1	876	1622	54.00740	0.6974	0	1099	2100	52.33333	0.8405	1	640	3682	17.381858	0.70160	0	1579	6178	25.5584331	0.949900	1	603	11.856075	0.377400	0	961	18.89501	0.2410	0	534	5000	10.680000	0.31600	0	254	1232	20.61688	0.6975	0	681	4763	14.297712	0.88510	1	3916	5086	76.99567	0.8096	1	2258	1028	45.527015	0.8820	1	0	0.000000	0.3251	0	28	2100	1.333333	0.5139	0	643	2100	30.61905	0.76370	1	57	5086	1.120724	0.7485	0	3.730500	0.8072	2	2.517000	0.5136	1	0.8096	0.8017	1	3.23320	0.81730	2	10.290300	0.7914	6	7543	3570	3054	1638	7543	21.715498	0.6364	0	320	4251	7.527641	0.7462	0	238	752	31.64894	0.6832	0	1211	2302	52.60643	0.6776	0	1449	3054	47.44597	0.8252	1	877	5631	15.574498	0.7611	1	1093	7543	14.4902559	0.9339	1	981	13.00544	0.282700	0	1174	15.56410	0.1785	0	756	6369.000	11.869995	0.37380	0	303	2013.000	15.05216	0.5737	0	970	7103	13.6562016	0.8846	1	5610	7543.000	74.37359	0.7916	1	3570	1871	52.4089636	0.8898	1	0.3216	258	3054	8.447937	0.8637	1	301	3054.000	9.855927	0.5207	0	15	7543	0.1988599	0.4315	0	3.9028	0.8603	3	2.293300	0.3701	1	0.7916	0.7845	1	3.0273	0.73680	2	10.015000	0.7805	7	0	0	0	Yes
34003018100	34	003	018100	NJ	New Jersey	Bergen County	1	Northeast Region	2	Middle Atlantic Division	6907	2665	2569	1865	6863	27.17470	0.7140	0	242	3781	6.400423	0.4509	0	434	834	52.03837	0.8694	1	1123	1735	64.72622	0.8830	1	1557	2569	60.60724	0.9450	1	1521	4649	32.716713	0.92270	1	2703	7124	37.9421673	0.992200	1	1024	14.825539	0.598800	0	1336	19.34270	0.2674	0	452	5848	7.729138	0.11920	0	363	1614	22.49071	0.7280	0	1324	6571	20.149140	0.93510	1	4209	6907	60.93818	0.7551	1	2665	517	19.399625	0.7487	0	0	0.000000	0.3251	0	136	2569	5.293889	0.7960	1	1043	2569	40.59945	0.82350	1	0	6907	0.000000	0.3512	0	4.024800	0.8697	3	2.648500	0.5885	1	0.7551	0.7477	1	3.04450	0.74620	2	10.472900	0.8112	7	7668	2912	2816	1803	7664	23.525574	0.6750	0	370	4727	7.827375	0.7646	1	441	819	53.84615	0.9501	1	1122	1997	56.18428	0.7544	1	1563	2816	55.50426	0.9274	1	1879	5775	32.536797	0.9576	1	1695	7668	22.1048513	0.9829	1	1041	13.57590	0.316600	0	1193	15.55816	0.1784	0	711	6474.819	10.981001	0.31250	0	197	1914.175	10.29164	0.3928	0	2045	7161	28.5574640	0.9756	1	5637	7667.630	73.51685	0.7875	1	2912	806	27.6785714	0.7973	1	0.3216	150	2816	5.326704	0.7742	1	833	2816.042	29.580522	0.7679	1	10	7668	0.1304121	0.3642	0	4.3075	0.9336	4	2.175900	0.2971	1	0.7875	0.7803	1	3.0252	0.73590	3	10.296100	0.8061	9	0	0	0	Yes
34005702101	34	005	702101	NJ	New Jersey	Burlington County	1	Northeast Region	2	Middle Atlantic Division	1637	702	483	445	1637	27.18387	0.7142	0	63	456	13.815789	0.8857	1	0	0	NaN	NA	NA	222	483	45.96273	0.5037	0	222	483	45.96273	0.7085	0	31	903	3.433001	0.08742	0	14	1965	0.7124682	0.008765	0	0	0.000000	0.002836	0	696	42.51680	0.9928	1	62	898	6.904232	0.08018	0	103	452	22.78761	0.7331	0	0	1379	0.000000	0.07335	0	248	1637	15.14966	0.4224	0	702	25	3.561254	0.4247	0	0	0.000000	0.3251	0	0	483	0.000000	0.1459	0	0	483	0.00000	0.01044	0	0	1637	0.000000	0.3512	0	2.404585	0.4890	1	1.882266	0.1557	1	0.4224	0.4183	0	1.25734	0.03853	0	5.966591	0.2021	2	3997	1271	1235	304	3996	7.607608	0.1919	0	46	901	5.105438	0.5252	0	0	0	NaN	NA	NA	731	1235	59.19028	0.8107	1	731	1235	59.19028	0.9566	1	49	1973	2.483528	0.0993	0	27	3057	0.8832188	0.0568	0	0	0.00000	0.001592	0	1651	41.30598	0.9924	1	58	1412.011	4.107616	0.01556	0	91	1092.793	8.32729	0.3046	0	32	3347	0.9560801	0.3989	0	1411	3996.883	35.30251	0.5750	0	1271	10	0.7867821	0.2414	0	0.3216	27	1235	2.186235	0.5699	0	11	1234.974	0.890707	0.0533	0	0	3997	0.0000000	0.1517	0	1.8298	0.3066	1	1.713052	0.1034	1	0.5750	0.5698	0	1.3379	0.06021	0	5.455752	0.1329	2	0	0	0	Yes

Code

# See total number of rows in data
svi_divisional_lihtc %>% nrow()

[1] 658

Code

# Filter SVI national data to remove all tracts that had a project in 2010 or before:
svi_national_lihtc <-  svi_national %>% 
  filter(! GEOID_2010_trt %in% lihtc_projects10$fips2010)

# Merge SVI national data with post 2010 project data, create flag for projects (1 for tracts that have LIHTC project, 0 for those that do not):
svi_national_lihtc <- left_join(svi_national_lihtc, 
                                  svi_national_lihtc20, 
                                  join_by("GEOID_2010_trt" == "GEOID_2010_trt")) %>% 
                        mutate(pre10_lihtc_project_cnt = replace_na(pre10_lihtc_project_cnt, 0),
                               post10_lihtc_project_cnt = replace_na(post10_lihtc_project_cnt, 0),
                                pre10_lihtc_project_dollars = replace_na(pre10_lihtc_project_dollars, 0),
                               post10_lihtc_project_dollars = replace_na(post10_lihtc_project_dollars, 0),
                               lihtc_flag = if_else(post10_lihtc_project_cnt >= 1, 1, 0))

# Finally, we want to filter our dataset to only have tracts that are eligible for the LIHTC program and that have SVI data:
svi_national_lihtc <- left_join(svi_national_lihtc, lihtc_eligible_flag, 
                                  join_by("GEOID_2010_trt" == "GEOID10")) %>%
                        filter(tolower(lihtc_eligibility) == "yes") %>%
                        filter(!is.na(F_TOTAL_10)) %>% 
                        filter(!is.na(F_TOTAL_20)) 


# View data
svi_national_lihtc %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

GEOID_2010_trt	FIPS_st	FIPS_county	FIPS_tract	state	state_name	county	region_number	region	division_number	division	E_TOTPOP_10	E_HU_10	E_HH_10	E_POV150_10	ET_POVSTATUS_10	EP_POV150_10	EPL_POV150_10	F_POV150_10	E_UNEMP_10	ET_EMPSTATUS_10	EP_UNEMP_10	EPL_UNEMP_10	F_UNEMP_10	E_HBURD_OWN_10	ET_HOUSINGCOST_OWN_10	EP_HBURD_OWN_10	EPL_HBURD_OWN_10	F_HBURD_OWN_10	E_HBURD_RENT_10	ET_HOUSINGCOST_RENT_10	EP_HBURD_RENT_10	EPL_HBURD_RENT_10	F_HBURD_RENT_10	E_HBURD_10	ET_HOUSINGCOST_10	EP_HBURD_10	EPL_HBURD_10	F_HBURD_10	E_NOHSDP_10	ET_EDSTATUS_10	EP_NOHSDP_10	EPL_NOHSDP_10	F_NOHSDP_10	E_UNINSUR_12	ET_INSURSTATUS_12	EP_UNINSUR_12	EPL_UNINSUR_12	F_UNINSUR_12	E_AGE65_10	EP_AGE65_10	EPL_AGE65_10	F_AGE65_10	E_AGE17_10	EP_AGE17_10	EPL_AGE17_10	E_DISABL_12	ET_DISABLSTATUS_12	EP_DISABL_12	EPL_DISABL_12	F_DISABL_12	E_SNGPNT_10	ET_FAMILIES_10	EP_SNGPNT_10	EPL_SNGPNT_10	F_SNGPNT_10	E_LIMENG_10	ET_POPAGE5UP_10	EP_LIMENG_10	EPL_LIMENG_10	E_MINRTY_10	ET_POPETHRACE_10	EP_MINRTY_10	EPL_MINRTY_10	F_MINRTY_10	E_STRHU_10	E_MUNIT_10	EP_MUNIT_10	EPL_MUNIT_10	F_MUNIT_10	E_MOBILE_10	EP_MOBILE_10	EPL_MOBILE_10	F_MOBILE_10	E_CROWD_10	ET_OCCUPANTS_10	EP_CROWD_10	EPL_CROWD_10	F_CROWD_10	E_NOVEH_10	ET_KNOWNVEH_10	EP_NOVEH_10	EPL_NOVEH_10	F_NOVEH_10	E_GROUPQ_10	ET_HHTYPE_10	EP_GROUPQ_10	EPL_GROUPQ_10	F_GROUPQ_10	SPL_THEME1_10	RPL_THEME1_10	F_THEME1_10	SPL_THEME2_10	RPL_THEME2_10	F_THEME2_10	SPL_THEME3_10	RPL_THEME3_10	F_THEME3_10	SPL_THEME4_10	RPL_THEME4_10	F_THEME4_10	SPL_THEMES_10	RPL_THEMES_10	F_TOTAL_10	E_TOTPOP_20	E_HU_20	E_HH_20	E_POV150_20	ET_POVSTATUS_20	EP_POV150_20	EPL_POV150_20	F_POV150_20	E_UNEMP_20	ET_EMPSTATUS_20	EP_UNEMP_20	EPL_UNEMP_20	F_UNEMP_20	E_HBURD_OWN_20	ET_HOUSINGCOST_OWN_20	EP_HBURD_OWN_20	EPL_HBURD_OWN_20	F_HBURD_OWN_20	E_HBURD_RENT_20	ET_HOUSINGCOST_RENT_20	EP_HBURD_RENT_20	EPL_HBURD_RENT_20	F_HBURD_RENT_20	E_HBURD_20	ET_HOUSINGCOST_20	EP_HBURD_20	EPL_HBURD_20	F_HBURD_20	E_NOHSDP_20	ET_EDSTATUS_20	EP_NOHSDP_20	EPL_NOHSDP_20	F_NOHSDP_20	E_UNINSUR_20	ET_INSURSTATUS_20	EP_UNINSUR_20	EPL_UNINSUR_20	F_UNINSUR_20	E_AGE65_20	EP_AGE65_20	EPL_AGE65_20	F_AGE65_20	E_AGE17_20	EP_AGE17_20	EPL_AGE17_20	E_DISABL_20	ET_DISABLSTATUS_20	EP_DISABL_20	EPL_DISABL_20	F_DISABL_20	E_SNGPNT_20	ET_FAMILIES_20	EP_SNGPNT_20	EPL_SNGPNT_20	F_SNGPNT_20	E_LIMENG_20	ET_POPAGE5UP_20	EP_LIMENG_20	EPL_LIMENG_20	E_MINRTY_20	ET_POPETHRACE_20	EP_MINRTY_20	EPL_MINRTY_20	F_MINRTY_20	E_STRHU_20	E_MUNIT_20	EP_MUNIT_20	EPL_MUNIT_20	F_MUNIT_20	E_MOBILE_20	EP_MOBILE_20	EPL_MOBILE_20	F_MOBILE_20	E_CROWD_20	ET_OCCUPANTS_20	EP_CROWD_20	EPL_CROWD_20	E_NOVEH_20	ET_KNOWNVEH_20	EP_NOVEH_20	EPL_NOVEH_20	F_NOVEH_20	E_GROUPQ_20	ET_HHTYPE_20	EP_GROUPQ_20	EPL_GROUPQ_20	F_GROUPQ_20	SPL_THEME1_20	RPL_THEME1_20	F_THEME1_20	SPL_THEME2_20	RPL_THEME2_20	F_THEME2_20	SPL_THEME3_20	RPL_THEME3_20	F_THEME3_20	SPL_THEME4_20	RPL_THEME4_20	F_THEME4_20	SPL_THEMES_20	RPL_THEMES_20	F_TOTAL_20	lihtc_eligibility
01005950700	01	005	950700	AL	Alabama	Barbour County	3	South Region	6	East South Central Division	1753	687	563	615	1628	37.77641	0.8088	1	17	667	2.548726	0.06941	0	41	376	10.90426	0.01945	0	62	187	33.15508	0.2464	0	103	563	18.29485	0.04875	0	264	1208	21.85430	0.7570	1	201	1527	13.163065	0.4991	0	368	20.992584	0.89510	1	462	26.354820	0.66130	211	1085	19.44700	0.7505	1	107	399	26.81704	0.8048	1	0	1628	0.000000	0.09298	861	1753	49.11580	0.7101	0	687	17	2.474527	0.4324	0	38	5.5312955	0.6970	0	3	563	0.5328597	0.3037	0	19	563	3.374778	0.3529	0	233	1753	13.29150	0.9517	1	2.18306	0.4137	2	3.20468	0.8377	3	0.7101	0.7035	0	2.7377	0.6100	1	8.83554	0.6264	6	1527	691	595	565	1365	41.39194	0.8765	1	37	572	6.468532	0.6776	0	70	376	18.617021	0.38590	0	92	219	42.00913	0.4736	0	162	595	27.22689	0.4454	0	280	1114	25.13465	0.8942	1	105	1378	7.619739	0.5505	0	383	25.081860	0.88450	1	337	22.069417	0.51380	237	1041.0000	22.76657	0.8360	1	144	413.0000	34.86683	0.9114	1	11	1466	0.7503411	0.40700	711	1527.0000	46.56189	0.6441	0	691	13	1.881331	0.3740	0	37	5.3545586	0.7152	0	0	595	0.0000000	0.09796	115	595.0000	19.327731	0.8859	1	149	1527	9.757695	0.9470	1	3.4442	0.7707	2	3.55270	0.9403	3	0.6441	0.6387	0	3.02006	0.7337	2	10.66106	0.8537	7	Yes
01011952100	01	011	952100	AL	Alabama	Bullock County	3	South Region	6	East South Central Division	1652	796	554	564	1652	34.14044	0.7613	1	46	816	5.637255	0.33630	0	96	458	20.96070	0.19930	0	62	96	64.58333	0.8917	1	158	554	28.51986	0.29220	0	271	1076	25.18587	0.8163	1	155	1663	9.320505	0.3183	0	199	12.046005	0.47180	0	420	25.423729	0.60240	327	1279	25.56685	0.9151	1	137	375	36.53333	0.9108	1	0	1590	0.000000	0.09298	1428	1652	86.44068	0.8939	1	796	0	0.000000	0.1224	0	384	48.2412060	0.9897	1	19	554	3.4296029	0.7145	0	45	554	8.122744	0.6556	0	0	1652	0.00000	0.3640	0	2.52440	0.5138	2	2.99308	0.7515	2	0.8939	0.8856	1	2.8462	0.6637	1	9.25758	0.6790	6	1382	748	549	742	1382	53.69030	0.9560	1	40	511	7.827789	0.7730	1	110	402	27.363184	0.71780	0	45	147	30.61224	0.2307	0	155	549	28.23315	0.4773	0	181	905	20.00000	0.8253	1	232	1382	16.787265	0.8813	1	164	11.866860	0.27170	0	250	18.089725	0.26290	258	1132.0000	22.79152	0.8368	1	99	279.0000	35.48387	0.9162	1	33	1275	2.5882353	0.64520	1347	1382.0000	97.46744	0.9681	1	748	0	0.000000	0.1079	0	375	50.1336898	0.9922	1	0	549	0.0000000	0.09796	37	549.0000	6.739526	0.6039	0	0	1382	0.000000	0.1831	0	3.9129	0.8785	4	2.93280	0.7342	2	0.9681	0.9599	1	1.98506	0.2471	1	9.79886	0.7570	8	Yes
01015000300	01	015	000300	AL	Alabama	Calhoun County	3	South Region	6	East South Central Division	3074	1635	1330	1904	3067	62.08021	0.9710	1	293	1362	21.512482	0.96630	1	180	513	35.08772	0.65450	0	383	817	46.87882	0.5504	0	563	1330	42.33083	0.70280	0	720	2127	33.85049	0.9148	1	628	2835	22.151675	0.8076	1	380	12.361744	0.49340	0	713	23.194535	0.45030	647	2111	30.64898	0.9708	1	298	773	38.55110	0.9247	1	0	2878	0.000000	0.09298	2623	3074	85.32856	0.8883	1	1635	148	9.051988	0.6465	0	6	0.3669725	0.4502	0	68	1330	5.1127820	0.8082	1	303	1330	22.781955	0.9029	1	0	3074	0.00000	0.3640	0	4.36250	0.9430	4	2.93218	0.7233	2	0.8883	0.8800	1	3.1718	0.8070	2	11.35478	0.9009	9	2390	1702	1282	1287	2390	53.84937	0.9566	1	102	1066	9.568480	0.8541	1	158	609	25.944171	0.67520	0	286	673	42.49629	0.4856	0	444	1282	34.63339	0.6634	0	467	1685	27.71513	0.9180	1	369	2379	15.510719	0.8562	1	342	14.309623	0.40850	0	548	22.928870	0.57100	647	1831.0000	35.33588	0.9862	1	202	576.0000	35.06944	0.9130	1	16	2134	0.7497657	0.40690	1896	2390.0000	79.33054	0.8451	1	1702	96	5.640423	0.5329	0	0	0.0000000	0.2186	0	0	1282	0.0000000	0.09796	186	1282.0000	14.508580	0.8308	1	43	2390	1.799163	0.7727	1	4.2483	0.9395	4	3.28560	0.8773	2	0.8451	0.8379	1	2.45296	0.4602	2	10.83196	0.8718	9	Yes
01015000500	01	015	000500	AL	Alabama	Calhoun County	3	South Region	6	East South Central Division	1731	1175	743	1042	1619	64.36072	0.9767	1	124	472	26.271186	0.98460	1	136	461	29.50108	0.48970	0	163	282	57.80142	0.7919	1	299	743	40.24226	0.64910	0	340	1270	26.77165	0.8389	1	460	1794	25.641026	0.8722	1	271	15.655690	0.70190	0	368	21.259388	0.32190	507	1449	34.98965	0.9885	1	150	386	38.86010	0.9269	1	0	1677	0.000000	0.09298	1559	1731	90.06355	0.9123	1	1175	50	4.255319	0.5128	0	4	0.3404255	0.4480	0	0	743	0.0000000	0.1238	0	122	743	16.419919	0.8473	1	0	1731	0.00000	0.3640	0	4.32150	0.9362	4	3.03218	0.7679	2	0.9123	0.9038	1	2.2959	0.3818	1	10.56188	0.8244	8	940	907	488	586	940	62.34043	0.9815	1	59	297	19.865320	0.9833	1	100	330	30.303030	0.79220	1	58	158	36.70886	0.3497	0	158	488	32.37705	0.6020	0	199	795	25.03145	0.8930	1	118	940	12.553192	0.7770	1	246	26.170213	0.90530	1	118	12.553192	0.08233	383	822.5089	46.56484	0.9984	1	30	197.8892	15.16000	0.5363	0	0	889	0.0000000	0.09479	898	940.3866	95.49264	0.9489	1	907	0	0.000000	0.1079	0	2	0.2205072	0.4456	0	2	488	0.4098361	0.23670	146	487.6463	29.939736	0.9404	1	0	940	0.000000	0.1831	0	4.2368	0.9379	4	2.61712	0.5593	2	0.9489	0.9409	1	1.91370	0.2196	1	9.71652	0.7468	8	Yes
01015000600	01	015	000600	AL	Alabama	Calhoun County	3	South Region	6	East South Central Division	2571	992	796	1394	2133	65.35396	0.9789	1	263	905	29.060773	0.98990	1	121	306	39.54248	0.75940	1	209	490	42.65306	0.4481	0	330	796	41.45729	0.68030	0	641	1556	41.19537	0.9554	1	416	1760	23.636364	0.8383	1	220	8.556982	0.24910	0	584	22.714897	0.41610	539	1353	39.83740	0.9955	1	243	466	52.14592	0.9783	1	30	2366	1.267963	0.48990	1944	2571	75.61260	0.8440	1	992	164	16.532258	0.7673	1	8	0.8064516	0.5110	0	46	796	5.7788945	0.8329	1	184	796	23.115578	0.9049	1	614	2571	23.88176	0.9734	1	4.44280	0.9548	4	3.12890	0.8088	2	0.8440	0.8362	1	3.9895	0.9792	4	12.40520	0.9696	11	1950	964	719	837	1621	51.63479	0.9467	1	157	652	24.079755	0.9922	1	22	364	6.043956	0.01547	0	129	355	36.33803	0.3420	0	151	719	21.00139	0.2303	0	363	1387	26.17159	0.9048	1	351	1613	21.760694	0.9435	1	249	12.769231	0.32090	0	356	18.256410	0.27140	332	1259.7041	26.35540	0.9135	1	136	435.6156	31.22018	0.8775	1	0	1891	0.0000000	0.09479	1463	1949.9821	75.02633	0.8219	1	964	14	1.452282	0.3459	0	8	0.8298755	0.5269	0	19	719	2.6425591	0.61120	197	719.0542	27.397100	0.9316	1	329	1950	16.871795	0.9655	1	4.0175	0.9001	4	2.47809	0.4764	2	0.8219	0.8149	1	3.38110	0.8712	2	10.69859	0.8583	9	Yes
01015002101	01	015	002101	AL	Alabama	Calhoun County	3	South Region	6	East South Central Division	3872	1454	1207	1729	2356	73.38710	0.9916	1	489	2020	24.207921	0.97860	1	20	168	11.90476	0.02541	0	718	1039	69.10491	0.9332	1	738	1207	61.14333	0.96900	1	113	725	15.58621	0.6035	0	664	3943	16.839970	0.6495	0	167	4.313016	0.05978	0	238	6.146694	0.02255	264	2359	11.19118	0.3027	0	94	263	35.74144	0.9050	1	46	3769	1.220483	0.48250	1601	3872	41.34814	0.6572	0	1454	761	52.338377	0.9504	1	65	4.4704264	0.6738	0	5	1207	0.4142502	0.2791	0	113	1207	9.362055	0.7004	0	1516	3872	39.15289	0.9860	1	4.19220	0.9133	3	1.77253	0.1304	1	0.6572	0.6511	0	3.5897	0.9337	2	10.21163	0.7885	6	3238	1459	1014	1082	1836	58.93246	0.9735	1	251	1403	17.890235	0.9767	1	31	155	20.000000	0.44920	0	515	859	59.95343	0.8554	1	546	1014	53.84615	0.9535	1	134	916	14.62882	0.7033	0	251	3238	7.751699	0.5588	0	167	5.157505	0.03597	0	169	5.219271	0.02111	323	1667.0000	19.37612	0.7205	0	94	277.0000	33.93502	0.9040	1	0	3164	0.0000000	0.09479	1045	3238.0000	32.27301	0.5125	0	1459	607	41.603838	0.9185	1	65	4.4551062	0.6949	0	24	1014	2.3668639	0.57900	85	1014.0000	8.382643	0.6775	0	1402	3238	43.298332	0.9876	1	4.1658	0.9263	3	1.77637	0.1225	1	0.5125	0.5082	0	3.85750	0.9661	2	10.31217	0.8160	6	Yes

Code

# See total number of rows in data
svi_national_lihtc %>% nrow()

[1] 3723

See how many tracts don’t have an LIHTC project post-2010 out of eligible tracts in our division and nationally:

Code

svi_divisional_lihtc %>% filter(lihtc_flag == 0) %>% nrow()

[1] 571

Code

svi_national_lihtc %>% filter(lihtc_flag == 0) %>% nrow()

[1] 3205

See how many tracts do have an LIHTC project post-2010 out of eligible tracts in our division:

Code

svi_divisional_lihtc %>% filter(lihtc_flag == 1) %>% nrow()

[1] 87

Code

svi_national_lihtc %>% filter(lihtc_flag == 1) %>% nrow()

[1] 518

View SVI DATA distributions:

National

Code

# See distribution of flags for SVI themes in top quarter in 2010
table(svi_national_lihtc$F_TOTAL_10)


  0   1   2   3   4   5   6   7   8   9  10  11  12  13  14 
  1  10  48  92 137 216 297 359 499 608 660 491 225  74   6

Code

# Average number of flags in 2010
mean(svi_national_lihtc$F_TOTAL_10)

[1] 8.465216

Code

# See distribution of flags for SVI themes in top quarter in 2020
table(svi_national_lihtc$F_TOTAL_20)


  0   1   2   3   4   5   6   7   8   9  10  11  12  13  14 
  8  21  49  92 175 265 364 443 557 626 552 346 181  40   4

Code

# Average number of flags in 2020
mean(svi_national_lihtc$F_TOTAL_20)

[1] 8.022831

Divisional

Code

# See distribution of flags for SVI themes in top quarter in 2010
table(svi_divisional_lihtc$F_TOTAL_10)


  0   1   2   3   4   5   6   7   8   9  10  11  12  13  14  15 
  1   8   9  14  34  40  45  72  82  99 101  83  47  19   2   2

Code

# Average number of flags in 2010
mean(svi_divisional_lihtc$F_TOTAL_10)

[1] 8.384498

Code

# See distribution of flags for SVI themes in top quarter in 2020
table(svi_divisional_lihtc$F_TOTAL_20)


 0  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 
 2  2 14 19 32 44 49 74 90 89 99 75 45 21  2  1

Code

# Average number of flags in 2020
mean(svi_divisional_lihtc$F_TOTAL_20)

[1] 8.265957

County-Level SVI LIHTC Data

Recall that we have data on counties in our data set:

Code

colnames(svi_divisional_lihtc) %>% head(11)

 [1] "GEOID_2010_trt"  "FIPS_st"         "FIPS_county"     "FIPS_tract"     
 [5] "state"           "state_name"      "county"          "region_number"  
 [9] "region"          "division_number" "division"

Therefore, just as with our NMTC data, we can summarize our project counts up to the county-level for easier visualizations with the following function NOTE: Remember to add all functions to project_data_steps.R :

Code

summarize_county_lihtc <- function(df) {
  # Find count of new NMTC projects after 2010 by county
  county_lihtc_project_cnt <- aggregate(df$post10_lihtc_project_cnt,
                                       by=list(State=df$state,
                                               County=df$county,
                                               Division=df$division), 
                                       FUN=sum) %>% 
                                      arrange(State, County) %>%
                                      rename("post10_lihtc_project_cnt" = "x")
  
  # Find count of census tracts in each county
  county_lihtc_tracts <- aggregate(df$GEOID_2010_trt,
                                  by=list(State=df$state,
                                          County=df$county,
                                          Division=df$division), 
                                  FUN=length) %>% 
                                  mutate(tract_cnt = x) %>% 
                                  select (-x)
  
  # Find sum of NMTC project dollars in each county
  county_lihtc_dollars <- aggregate(df$post10_lihtc_project_dollars,
                                   by=list(State=df$state,
                                           County=df$county,
                                           Division=df$division), 
                                   FUN=sum) %>% 
                                  arrange(State, County) %>%
                                  rename("post10_lihtc_project_dollars" = "x")
  
  # Create character column with NMTC dollars formatted as currency
  county_lihtc_dollars$post10_lihtc_dollars_formatted <-
    scales::dollar_format()(county_lihtc_dollars$post10_lihtc_project_dollars)

  # Join project counts and census tract counts datasets
  county_lihtc0 <- left_join(county_lihtc_project_cnt, county_lihtc_tracts,
                            join_by("State" == "State",
                                    "County" == "County",
                                    "Division" == "Division"))

  # Add dollar amounts
  county_lihtc <- left_join(county_lihtc0, county_lihtc_dollars,
                         join_by("State" == "State",
                                 "County" == "County",
                                 "Division" == "Division"))
  
  # Output data
  return(county_lihtc)
}

Code

svi_national_lihtc_county_sum <- summarize_county_lihtc(svi_national_lihtc)

svi_national_lihtc_county_sum %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

State	County	Division	tract_cnt	post10_lihtc_dollars_formatted
AK	Bethel Census Area	Pacific Division	2	$0
AK	Dillingham Census Area	Pacific Division	1	$0
AK	Kenai Peninsula Borough	Pacific Division	1	$0
AK	Nome Census Area	Pacific Division	1	$0
AK	Yukon-Koyukuk Census Area	Pacific Division	2	$0
AL	Barbour County	East South Central Division	1	$0

Code

svi_divisional_lihtc_county_sum <- summarize_county_lihtc(svi_divisional_lihtc)
svi_divisional_lihtc_county_sum %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

State	County	Division	post10_lihtc_project_cnt	tract_cnt	post10_lihtc_project_dollars	post10_lihtc_dollars_formatted
NJ	Atlantic County	Middle Atlantic Division	1	3	1497998	$1,497,998
NJ	Bergen County	Middle Atlantic Division	0	2	0	$0
NJ	Burlington County	Middle Atlantic Division	0	2	0	$0
NJ	Camden County	Middle Atlantic Division	1	6	0	$0
NJ	Cape May County	Middle Atlantic Division	0	2	0	$0
NJ	Cumberland County	Middle Atlantic Division	0	1	0	$0

We can then utilize our flag_summarize function from Lab 03 to find our county-level SVI flag calculations:

Code

# Create data frame of LIHTC eligible tracts 2010 nationally
svi_national_lihtc10 <- svi_national_lihtc %>% select(GEOID_2010_trt, FIPS_st, FIPS_county, 
    state, state_name, county, region_number, region, division_number, 
    division, F_TOTAL_10, E_TOTPOP_10) %>% rename("F_TOTAL" = "F_TOTAL_10")

# Count national-level SVI flags for 2010, create unified fips column
svi_2010_national_county_flags_lihtc <- flag_summarize(svi_national_lihtc10, "E_TOTPOP_10") %>% unite("fips_county_st", FIPS_st:FIPS_county, remove = FALSE, sep="")

# Add suffix to flag columns 2010
colnames(svi_2010_national_county_flags_lihtc)[11:15] <- paste0(colnames(svi_2010_national_county_flags_lihtc)[11:15], 10)

# Create data frame of LIHTC eligible tracts 2020 nationally
svi_national_lihtc20 <- svi_national_lihtc %>% select(GEOID_2010_trt, FIPS_st, FIPS_county, 
    state, state_name, county, region_number, region, division_number, 
    division, F_TOTAL_20, E_TOTPOP_20) %>% rename("F_TOTAL" = "F_TOTAL_20")

# Count national-level SVI flags for 2020, create unified fips column
svi_2020_national_county_flags_lihtc <- flag_summarize(svi_national_lihtc20, "E_TOTPOP_20") %>% unite("fips_county_st", FIPS_st:FIPS_county, remove = FALSE, sep="")

# Identify needed columns for 2020, add suffix
colnames(svi_2020_national_county_flags_lihtc)[11:15] <- paste0(colnames(svi_2020_national_county_flags_lihtc)[11:15], "20")

# Filter to needed columns for 2020 to avoid duplicate column column names
svi_2020_national_county_flags_join_lihtc <- svi_2020_national_county_flags_lihtc %>% ungroup() %>% select("fips_county_st", all_of(colnames(svi_2020_national_county_flags_lihtc)[11:15]))
 
# Join 2010 and 2020 data
svi_national_county_flags_lihtc <- left_join(svi_2010_national_county_flags_lihtc, svi_2020_national_county_flags_join_lihtc, join_by("fips_county_st" == "fips_county_st")) 

svi_national_county_flags_lihtc %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

fips_county_st	FIPS_st	FIPS_county	state	state_name	county	region_number	region	division_number	division	flag_count10	pop10	flag_by_pop10	flag_count_quantile10	flag_pop_quantile10	flag_count20	pop20	flag_by_pop20	flag_count_quantile20	flag_pop_quantile20
01005	01	005	AL	Alabama	Barbour County	3	South Region	6	East South Central Division	6	1753	0.0034227	0.2	0.8	7	1527	0.0045842	0.2	1.0
01011	01	011	AL	Alabama	Bullock County	3	South Region	6	East South Central Division	6	1652	0.0036320	0.2	0.8	8	1382	0.0057887	0.4	1.0
01015	01	015	AL	Alabama	Calhoun County	3	South Region	6	East South Central Division	40	15130	0.0026438	0.8	0.6	37	11783	0.0031401	0.8	0.8
01023	01	023	AL	Alabama	Choctaw County	3	South Region	6	East South Central Division	12	5578	0.0021513	0.6	0.4	15	5412	0.0027716	0.6	0.8
01031	01	031	AL	Alabama	Coffee County	3	South Region	6	East South Central Division	12	8139	0.0014744	0.6	0.2	13	8517	0.0015264	0.6	0.2
01033	01	033	AL	Alabama	Colbert County	3	South Region	6	East South Central Division	10	1983	0.0050429	0.4	1.0	8	1931	0.0041429	0.4	1.0

Join flags with LIHTC county project summary data:

Code

svi_national_county_lihtc <- left_join(svi_national_lihtc_county_sum,
                                      svi_national_county_flags_lihtc,
                                    join_by("State" == "state", "County" == "county",
                                            "Division" == "division"))

svi_national_county_lihtc$post10_lihtc_project_cnt[is.na(svi_national_county_lihtc$post10_lihtc_project_cnt)] <- 0

svi_national_county_lihtc$county_name <- paste0(svi_national_county_lihtc$County, ", ", svi_national_county_lihtc$State)

svi_national_county_lihtc %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

State	County	Division	tract_cnt	post10_lihtc_dollars_formatted	fips_county_st	FIPS_st	FIPS_county	state_name	region_number	region	division_number	flag_count10	pop10	flag_by_pop10	flag_count_quantile10	flag_pop_quantile10	flag_count20	pop20	flag_by_pop20	flag_count_quantile20	flag_pop_quantile20	county_name
AK	Bethel Census Area	Pacific Division	2	$0	02050	02	050	Alaska	4	West Region	9	18	10867	0.0016564	0.6	0.4	20	11715	0.0017072	0.8	0.4	Bethel Census Area, AK
AK	Dillingham Census Area	Pacific Division	1	$0	02070	02	070	Alaska	4	West Region	9	9	2569	0.0035033	0.4	0.8	10	2801	0.0035702	0.4	0.8	Dillingham Census Area, AK
AK	Kenai Peninsula Borough	Pacific Division	1	$0	02122	02	122	Alaska	4	West Region	9	7	251	0.0278884	0.2	1.0	8	531	0.0150659	0.4	1.0	Kenai Peninsula Borough, AK
AK	Nome Census Area	Pacific Division	1	$0	02180	02	180	Alaska	4	West Region	9	9	5766	0.0015609	0.4	0.2	10	5901	0.0016946	0.4	0.4	Nome Census Area, AK
AK	Yukon-Koyukuk Census Area	Pacific Division	2	$0	02290	02	290	Alaska	4	West Region	9	18	2300	0.0078261	0.6	1.0	21	2153	0.0097538	0.8	1.0	Yukon-Koyukuk Census Area, AK
AL	Barbour County	East South Central Division	1	$0	01005	01	005	Alabama	3	South Region	6	6	1753	0.0034227	0.2	0.8	7	1527	0.0045842	0.2	1.0	Barbour County, AL

Code

# Create data frame of LIHTC eligible tracts 2020 nationally
svi_divisional_lihtc10 <- svi_divisional_lihtc %>% select(GEOID_2010_trt, FIPS_st, FIPS_county, 
    state, state_name, county, region_number, region, division_number, 
    division, F_TOTAL_10, E_TOTPOP_10) %>% rename("F_TOTAL" = "F_TOTAL_10")

# Count divisional-level SVI flags for 2010, create unified fips column
svi_2010_divisional_county_flags_lihtc <- flag_summarize(svi_divisional_lihtc10, "E_TOTPOP_10") %>% unite("fips_county_st", FIPS_st:FIPS_county, remove = FALSE, sep="")

# Add suffix to flag columns 2010
colnames(svi_2010_divisional_county_flags_lihtc)[11:15] <- paste0(colnames(svi_2010_divisional_county_flags_lihtc)[11:15], "10")

# Create data frame of LIHTC eligible tracts 2020 nationally
svi_divisional_lihtc20 <- svi_divisional_lihtc %>% select(GEOID_2010_trt, FIPS_st, FIPS_county, 
    state, state_name, county, region_number, region, division_number, 
    division, F_TOTAL_20, E_TOTPOP_20) %>% rename("F_TOTAL" = "F_TOTAL_20")

# Count divisional-level SVI flags for 2020, create unified fips column
svi_2020_divisional_county_flags_lihtc <- flag_summarize(svi_divisional_lihtc20, "E_TOTPOP_20") %>% unite("fips_county_st", FIPS_st:FIPS_county, remove = FALSE, sep="")

# Identify needed columns for 2020
colnames(svi_2020_divisional_county_flags_lihtc)[11:15] <- paste0(colnames(svi_2020_divisional_county_flags_lihtc)[11:15], "20")

# Filter to needed columns for 2020 to avoid duplicate column column names
svi_2020_divisional_county_flags_join_lihtc <- svi_2020_divisional_county_flags_lihtc %>% ungroup() %>% select("fips_county_st", all_of(colnames(svi_2020_divisional_county_flags_lihtc)[11:15]))
 
# Join 2010 and 2020 data
svi_divisional_county_flags_lihtc <- left_join(svi_2010_divisional_county_flags_lihtc, svi_2020_divisional_county_flags_join_lihtc, join_by("fips_county_st" == "fips_county_st")) 

svi_divisional_county_flags_lihtc %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

fips_county_st	FIPS_st	FIPS_county	state	state_name	county	region_number	region	division_number	division	flag_count10	pop10	flag_by_pop10	flag_count_quantile10	flag_pop_quantile10	flag_count20	pop20	flag_by_pop20	flag_count_quantile20	flag_pop_quantile20
34001	34	001	NJ	New Jersey	Atlantic County	1	Northeast Region	2	Middle Atlantic Division	35	7939	0.0044086	0.8	1.0	37	8027	0.0046094	0.8	1.0
34003	34	003	NJ	New Jersey	Bergen County	1	Northeast Region	2	Middle Atlantic Division	13	11993	0.0010840	0.6	0.2	16	15211	0.0010519	0.6	0.2
34005	34	005	NJ	New Jersey	Burlington County	1	Northeast Region	2	Middle Atlantic Division	11	4637	0.0023722	0.4	0.6	6	6493	0.0009241	0.2	0.2
34007	34	007	NJ	New Jersey	Camden County	1	Northeast Region	2	Middle Atlantic Division	72	22516	0.0031977	1.0	0.8	61	20790	0.0029341	0.8	0.8
34009	34	009	NJ	New Jersey	Cape May County	1	Northeast Region	2	Middle Atlantic Division	15	5839	0.0025689	0.6	0.8	10	5394	0.0018539	0.4	0.4
34011	34	011	NJ	New Jersey	Cumberland County	1	Northeast Region	2	Middle Atlantic Division	10	1053	0.0094967	0.4	1.0	10	801	0.0124844	0.4	1.0

Join flags with LIHTC county project summary data for division:

Code

svi_divisional_county_lihtc <- left_join(svi_divisional_lihtc_county_sum, 
                                        svi_divisional_county_flags_lihtc,
                                    join_by("State" == "state", "County" == "county",
                                            "Division" == "division"))

svi_divisional_county_lihtc$post10_lihtc_project_cnt[is.na(svi_divisional_county_lihtc $post10_lihtc_project_cnt)] <- 0

svi_divisional_county_lihtc$county_name <- paste0(svi_divisional_county_lihtc$County, ", ", svi_divisional_county_lihtc$State)

svi_divisional_county_lihtc %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

State	County	Division	post10_lihtc_project_cnt	tract_cnt	post10_lihtc_project_dollars	post10_lihtc_dollars_formatted	fips_county_st	FIPS_st	FIPS_county	state_name	region_number	region	division_number	flag_count10	pop10	flag_by_pop10	flag_count_quantile10	flag_pop_quantile10	flag_count20	pop20	flag_by_pop20	flag_count_quantile20	flag_pop_quantile20	county_name
NJ	Atlantic County	Middle Atlantic Division	1	3	1497998	$1,497,998	34001	34	001	New Jersey	1	Northeast Region	2	35	7939	0.0044086	0.8	1.0	37	8027	0.0046094	0.8	1.0	Atlantic County, NJ
NJ	Bergen County	Middle Atlantic Division	0	2	0	$0	34003	34	003	New Jersey	1	Northeast Region	2	13	11993	0.0010840	0.6	0.2	16	15211	0.0010519	0.6	0.2	Bergen County, NJ
NJ	Burlington County	Middle Atlantic Division	0	2	0	$0	34005	34	005	New Jersey	1	Northeast Region	2	11	4637	0.0023722	0.4	0.6	6	6493	0.0009241	0.2	0.2	Burlington County, NJ
NJ	Camden County	Middle Atlantic Division	1	6	0	$0	34007	34	007	New Jersey	1	Northeast Region	2	72	22516	0.0031977	1.0	0.8	61	20790	0.0029341	0.8	0.8	Camden County, NJ
NJ	Cape May County	Middle Atlantic Division	0	2	0	$0	34009	34	009	New Jersey	1	Northeast Region	2	15	5839	0.0025689	0.6	0.8	10	5394	0.0018539	0.4	0.4	Cape May County, NJ
NJ	Cumberland County	Middle Atlantic Division	0	1	0	$0	34011	34	011	New Jersey	1	Northeast Region	2	10	1053	0.0094967	0.4	1.0	10	801	0.0124844	0.4	1.0	Cumberland County, NJ

National Exploratory Data Analysis: Visualizing The Intervention

Now that we have our NMTC and LIHTC data sets created, let’s create some visualizations to better examine our data:

NMTC

Correlation between outcome & intervention

To begin, let’s explore the relationship between SVI flag counts in 2010 and the amount of NMTC dollars received from 2011-2020 by county nationally.

We can accomplish this by reviewing our summary statistics, a scatterplot, and a calculation of Pearson’s r to measure the correlation.

First let’s create a dataset of only counties with projects:

Code

svi_national_county_nmtc_projects <- svi_national_county_nmtc %>% filter(post10_nmtc_project_cnt > 0)

Now let’s review the summary statistics for our data set:

Code

summary(svi_national_county_nmtc_projects$flag_count10)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
      0      19      40     177     132    9936

Code

summary(svi_national_county_nmtc_projects$post10_nmtc_project_dollars)

     Min.   1st Qu.    Median      Mean   3rd Qu.      Max. 
     5154   5970000  12760000  30332743  28505000 987407086

As we can see from the summary statistics, there’s quite a spread of values across counties from 0 SVI flags to over 9,000 and ~$5,000 in tax credits to nearly $1bn. Let’s view this visually in a scatterplot:

Code

# Scatterplot
# y is our independent variable (NMTC Project Dollars),  
# x is our dependent variable (SVI flag count)
ggplot2::ggplot(svi_national_county_nmtc_projects,
                aes(x=flag_count10,
                    y=post10_nmtc_project_dollars)) +
        geom_point() +
        geom_smooth(method="lm") +
        scale_y_continuous(labels = scales::dollar_format())

Code

# Pearson's r calculation
cor(svi_national_county_nmtc_projects$flag_count10, svi_national_county_nmtc_projects$post10_nmtc_project_dollars, method = "pearson")

[1] 0.8197007

Here, we can see that when we consider ALL counties, we have a very strong positive correlation between SVI Flag Counts in 2010, suggesting that counties that had more social vulnerability in 2010 received more NMTC tax credit dollars in 2011-2020.

However, upon further inspection, we can also see that our data is not in a continuous line. Rather, we have the majority of our data clustered in the bottom left corner, a few scattered towards the middle and a single data point all the way in the top right of our plot.

We can use a box plot to look closer at this:

Code

boxplot(svi_national_county_nmtc_projects$flag_count10)

Code

boxplot.stats(svi_national_county_nmtc_projects$flag_count10)$out %>% sort(decreasing = TRUE)

  [1] 9936 5111 3732 3561 2941 2537 2508 2453 2296 2279 1906 1731 1569 1489 1486
 [16] 1436 1110 1106 1096 1057 1013 1004  995  991  984  977  960  942  919  871
 [31]  854  850  836  822  795  774  759  746  731  728  718  714  705  701  691
 [46]  682  651  650  641  629  595  572  571  569  564  546  541  531  517  499
 [61]  491  487  484  468  467  463  461  458  458  455  451  442  429  423  422
 [76]  413  413  408  401  399  389  381  378  378  377  374  369  363  362  358
 [91]  356  355  352  350  349  349  342  341  338  328  326  318  316  313

Similar to our observations in our correlation plot, we can see that there are several values that fall outside the majority cluster of our dataset, known as outliers. However, one point in particular, stands out even amongst the outliers and that is our county with 9,936 SVI Flags in 2010. This data point is known as an influential point since it’s extreme value can alter the outcomes of our model.

In some instances it is prudent to remove outliers that can skew regression models. However, in cases where the outlier is a natural occurrence and not an error within the data set or sampling methodology, omitting the outlier can result in faulty conclusions.

Thus, it’s important that we examine this data point further.

We can filter our data set to identify it as Los Angeles County, CA:

Code

svi_national_county_nmtc_projects %>% filter(flag_count10 == 9936) %>% head() %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

State	County	Division	post10_nmtc_project_cnt	tract_cnt	post10_nmtc_project_dollars	post10_nmtc_dollars_formatted	fips_county_st	FIPS_st	FIPS_county	state_name	region_number	region	division_number	flag_count10	pop10	flag_by_pop10	flag_count_quantile10	flag_pop_quantile10	flag_count20	pop20	flag_by_pop20	flag_count_quantile20	flag_pop_quantile20	county_name
CA	Los Angeles County	Pacific Division	72	1070	987407086	$987,407,086	06037	06	037	California	4	West Region	9	9936	4431665	0.002242	1	1	9098	4529210	0.0020087	1	1	Los Angeles County, CA

Code

svi_national_nmtc %>% filter(county == "Los Angeles County") %>% select(GEOID_2010_trt, F_TOTAL_10, post10_nmtc_dollars) %>% summary()

 GEOID_2010_trt       F_TOTAL_10     post10_nmtc_dollars
 Length:1070        Min.   : 2.000   Min.   :       0   
 Class :character   1st Qu.: 8.000   1st Qu.:       0   
 Mode  :character   Median :10.000   Median :       0   
                    Mean   : 9.286   Mean   :  922810   
                    3rd Qu.:11.000   3rd Qu.:       0   
                    Max.   :15.000   Max.   :76845100

Looking at the summary stats for LA County, we can quickly conclude that we have not made an error in our calculations, there are indeed 1,070 tracts in our Los Angeles data set and with a median total SVI Flag count (at top 25% vulnerability) of 10 per tract, it’s reasonable to have ~10,000 flags.

Code

1070*10

[1] 10700

Similarly, the max tract has $76,845,100 NMTC dollars while the mean tract has $922,810 dollars.

Therefore, we can conclude that there is no reason to exclude LA County from our national analysis of the relationship between SVI Flag Counts in 2010 and NMTC Dollars from 2011-2020.

But what if we want to know the relationship between SVI Flag Counts and NMTC dollars in the majority of our counties?

To discover this, we can utilize an algorithm known as k-means clustering to create clusters within our data set and examine each of the groupings separately.

K-Means Clustering

As previously stated, we will be using the machine learning technique K-Means Clustering to identify smaller groupings of data in our dataset and evaluate the strength of the relationship between 2010 Flag Count and NMTC Dollars in 2011-2020 in the absence of the influential point.

To accomplish this, we first need to create a dataset of just our variables of interest and set our county_name column to the rownames since only numeric values can be entered into the kmeans() function.

We also want to double-check that all null values are absent from the data set and use scale() to convert our data to a comparable range:

Code

svi_national_nmtc_cluster <- svi_national_county_nmtc_projects %>% 
                            select(county_name, post10_nmtc_project_dollars, 
                                   flag_count10) %>% 
                            remove_rownames %>% 
                            column_to_rownames(var="county_name")

# Remove nulls, if in dataset
svi_national_nmtc_cluster <- na.omit(svi_national_nmtc_cluster)


# Scale numeric variables
svi_national_nmtc_cluster <- scale(svi_national_nmtc_cluster)


svi_national_nmtc_cluster %>% head(5)

                              post10_nmtc_project_dollars flag_count10
Aleutians East Borough, AK                     -0.2125961   -0.3189664
Anchorage Municipality, AK                     -0.2995956   -0.1981871
Wade Hampton Census Area, AK                   -0.1300468   -0.3170792
Yukon-Koyukuk Census Area, AK                  -0.3310540   -0.2831100
Baldwin County, AL                             -0.1906291   -0.2698998

Next we can try a few different cluster numbers and allow the algorithm to search through 25 sets to identify the best groupings for each number:

Code

set.seed(123)
k2_nmtc_nat <- kmeans(svi_national_nmtc_cluster, centers = 2, nstart = 25)
set.seed(123)
k3_nmtc_nat <- kmeans(svi_national_nmtc_cluster, centers = 3, nstart = 25)
set.seed(123)
k4_nmtc_nat <- kmeans(svi_national_nmtc_cluster, centers = 4, nstart = 25)
set.seed(123)
k5_nmtc_nat <- kmeans(svi_national_nmtc_cluster, centers = 5, nstart = 25)

Next we can view the plots to visually check the groupings and see if there’s any overlap:

Code

# plots to compare
p_k2_nmtc_nat <- factoextra::fviz_cluster(k2_nmtc_nat, geom = "point", data = svi_national_nmtc_cluster) + ggtitle("k = 2")

p_k3_nmtc_nat <- factoextra::fviz_cluster(k3_nmtc_nat, geom = "point", data = svi_national_nmtc_cluster) + ggtitle("k = 3")

p_k4_nmtc_nat <- factoextra::fviz_cluster(k4_nmtc_nat, geom = "point",  data = svi_national_nmtc_cluster) + ggtitle("k = 4")

p_k5_nmtc_nat <- factoextra::fviz_cluster(k5_nmtc_nat, geom = "point",  data = svi_national_nmtc_cluster) + ggtitle("k = 5")

grid.arrange(p_k2_nmtc_nat, p_k3_nmtc_nat, p_k4_nmtc_nat, p_k5_nmtc_nat, nrow = 2)

While we can visually look through these to see that group counts 3 and 4 appear to provide the best options without too much overlap, we can remove the potentially fallacies of visual inspection by employing the usage of an Elbow Plot which will measure the variances between the groups to identify which group number is optimal before the changes in group size start to have a negligible effect on analysis.

Code

elbow_plot <- function(df) {
  
  # Code source: https://uc-r.github.io/kmeans_clustering
  
  # Repeats same outcome each time run
  set.seed(123)

  # function to compute total within-cluster sum of square 
  wss <- function(k) {
    print(k)
    kmeans(df, k, nstart = 10, iter.max=25  )$tot.withinss
  }
  
  # Compute and plot wss for k = 1 to k = 15 (or one less than nrow(15) if row count is <= 15)
  if (nrow(df) > 15) {
    k.values <- 1:15
    print(k.values)
  } else {
    end <- nrow(df)-1
    k.values <- 1:end
    print(k.values)
  }
  
  # extract wss for 2-15 clusters (or one less than nrow(15) if row count is <= 15)
  wss_values <- map_dbl(k.values, wss)
  
  plot(k.values, wss_values,
         type="b", pch = 19, frame = FALSE, 
         xlab="Number of clusters K",
         ylab="Total within-clusters sum of squares")  
}

Code

elbow_plot(svi_national_nmtc_cluster)

[1] 1
[1] 2
[1] 3
[1] 4
[1] 5
[1] 6
[1] 7
[1] 8
[1] 9
[1] 10
[1] 11
[1] 12
[1] 13
[1] 14
[1] 15

Here we can see that the spacing between clusters decreases substantially after 3. Thus, we will go with 3 clusters:

Code

p_k3_nmtc_nat <- factoextra::fviz_cluster(k3_nmtc_nat, geom = "point", data = svi_national_nmtc_cluster) + ggtitle("k = 3")

p_k3_nmtc_nat

We can then transform our cluster matrix back to a data frame and assign these clusters to our counties:

Code

svi_national_nmtc_cluster_label <- as.data.frame(svi_national_nmtc_cluster) %>%
                                  rownames_to_column(var = "county_name") %>%
                                  as_tibble() %>%
                                  mutate(cluster = k3_nmtc_nat$cluster) %>%
                                  select(county_name, cluster)

svi_national_county_nmtc_projects2 <- left_join(svi_national_county_nmtc_projects, svi_national_nmtc_cluster_label, join_by(county_name == county_name))

# View county counts in each cluster
table(svi_national_county_nmtc_projects2$cluster)


  1   2   3 
  2  27 758

Now we can re-examine the correlation between 2010 SVI Flag Counts and NMTC Project Dollars for each subset of our data.

First recall our overall outcomes:

Code

# Overall Scatterplot
# y is our independent variable (NMTC Project Dollars),  
# x is our dependent variable (SVI flag count)
ggplot2::ggplot(svi_national_county_nmtc_projects2,
                aes(x=flag_count10,
                    y=post10_nmtc_project_dollars)) +
        geom_point() +
        geom_smooth(method="lm") +
        scale_y_continuous(labels = scales::dollar_format())

Code

# Pearson's r calculation
cor(svi_national_county_nmtc_projects2$flag_count10, svi_national_county_nmtc_projects2$post10_nmtc_project_dollars, method = "pearson")

[1] 0.8197007

Now let’s look at our our high end counties in cluster 1:

Code

# Cluster 1 Scatterplot
# y is our independent variable (NMTC Project Dollars),  
# x is our dependent variable (SVI flag count)

svi_national_county_nmtc_projects2 %>% 
  filter(cluster == 1) %>%
  ggplot2::ggplot(aes(x=flag_count10,
                    y=post10_nmtc_project_dollars)) +
        geom_point() +
        geom_smooth(method="lm") +
        scale_y_continuous(labels = scales::dollar_format())

Code

svi_national_county_nmtc_projects2 %>% 
  filter(cluster == 1) %>%
  select(flag_count10,post10_nmtc_project_dollars) %>%
  cor(method = "pearson")

                            flag_count10 post10_nmtc_project_dollars
flag_count10                           1                           1
post10_nmtc_project_dollars            1                           1

As expected, we see a very high correlation where there’s only 2 counties with SVI flag counts above 5,000 and there’s a perfect relationship where the county with the higher SVI flag count received more money than the lower value.

We can see these two counties here:

Code

svi_national_county_nmtc_projects2 %>% 
  filter(cluster == 1) %>%
  select(county_name, flag_count10, post10_nmtc_dollars_formatted) %>% arrange(flag_count10) %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

county_name	flag_count10	post10_nmtc_dollars_formatted
Cook County, IL	5111	$790,158,215
Los Angeles County, CA	9936	$987,407,086

Now let’s examine our data for Cluster 2 (mid-range data):

Code

# Cluster 2 Scatterplot
# y is our independent variable (NMTC Project Dollars),  
# x is our dependent variable (SVI flag count)

svi_national_county_nmtc_projects2 %>% 
  filter(cluster == 2) %>%
  ggplot2::ggplot(aes(x=flag_count10,
                    y=post10_nmtc_project_dollars)) +
        geom_point() +
        geom_smooth(method="lm") +
        scale_y_continuous(labels = scales::dollar_format())

Code

svi_national_county_nmtc_projects2 %>% 
  filter(cluster == 2) %>%
  select(flag_count10,post10_nmtc_project_dollars) %>%
  cor(method = "pearson")

                            flag_count10 post10_nmtc_project_dollars
flag_count10                  1.00000000                 -0.05722041
post10_nmtc_project_dollars  -0.05722041                  1.00000000

As we can see here, our mid range points are scattered and have a very weak correlation that skews slightly negative, but doesn’t have enough strength for us to confidently draw conclusions.

Rather, it seems the amount of money given to counties with 500 - 5,000 SVI flags varied widely between just under $100 million to just over $500 million.

We can view these counties here:

Code

svi_national_county_nmtc_projects2 %>% 
  filter(cluster == 2) %>%
  select(county_name, flag_count10, post10_nmtc_dollars_formatted) %>% arrange(flag_count10) %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

county_name	flag_count10	post10_nmtc_dollars_formatted
Hennepin County, MN	564	$173,393,000
District of Columbia, DC	595	$377,155,570
Hamilton County, OH	629	$397,543,856
Jackson County, MO	651	$201,937,281
Suffolk County, MA	701	$192,010,188
Orleans Parish, LA	718	$233,891,078
Allegheny County, PA	731	$244,342,400
Fulton County, GA	795	$437,737,000
New York County, NY	850	$255,545,686
Marion County, IN	919	$138,426,520
Baltimore city, MD	960	$333,109,232
Milwaukee County, WI	984	$315,495,493
Shelby County, TN	1004	$289,352,388
Fresno County, CA	1110	$115,258,480
Bexar County, TX	1436	$199,964,269
Clark County, NV	1486	$225,315,967
Cuyahoga County, OH	1489	$306,121,487
San Diego County, CA	1569	$221,738,411
Philadelphia County, PA	1906	$550,969,964
Queens County, NY	2279	$85,225,100
Miami-Dade County, FL	2296	$233,661,603
Maricopa County, AZ	2453	$84,923,464
Dallas County, TX	2508	$302,019,013
Bronx County, NY	2537	$306,355,715
Wayne County, MI	2941	$360,949,480
Harris County, TX	3561	$262,456,477
Kings County, NY	3732	$216,348,600

Finally, let’s look at the majority of our data (low SVI flag count, low NMTC dollars) in cluster 3:

Code

# Cluster 3 Scatterplot
# y is our independent variable (NMTC Project Dollars),  
# x is our dependent variable (SVI flag count)

svi_national_county_nmtc_projects2 %>% 
  filter(cluster == 3) %>%
  ggplot2::ggplot(aes(x=flag_count10,
                    y=post10_nmtc_project_dollars)) +
        geom_point() +
        geom_smooth(method="lm") +
        scale_y_continuous(labels = scales::dollar_format())

Code

svi_national_county_nmtc_projects2 %>% 
  filter(cluster == 3) %>%
  select(flag_count10,post10_nmtc_project_dollars) %>%
  cor(method = "pearson")

                            flag_count10 post10_nmtc_project_dollars
flag_count10                   1.0000000                   0.4736348
post10_nmtc_project_dollars    0.4736348                   1.0000000

So here we can see out correlation has dropped from very strong to moderate. While the trend of the line still suggests there’s a positive relationship, we can confirm that LA County has a strong influence on our correlation.

Thus, we can conclude here that there is a pattern where counties with lower counts of flags have a moderately positive correlation between more vulnerable counties receiving more NMTC money than less vulnerable counties and counties with the highest counts of SVI flags also following a pattern of more vulnerable counties receiving more NMTC dollars.

Our mid-level counties do not have such a clear pattern on a national level, though they may rank differently divisionally.

Bivariate Map

Now let’s view this relationship spatially by creating a bivariate map.

First, we’ll pull county and state shapefile data for the entire US (Note: We already have this data for our divisions, so we will not need to re-run it. )

Code

# Recall that we are working with 2010 census tracts, thus we need to pull the 2010 shapefiles
county_sf = tigris::counties(year = 2010, cb = TRUE)

# Shift geometric locations of AK and HI
county_sf <- shift_geometry(
              county_sf,
              geoid_column = NULL,
              preserve_area = FALSE,
              position = c("below", "outside")
            )

st_sf <- tigris::states(year = 2010, cb = TRUE) %>% filter(STATE != "72")

# Shift geometric locations of AK and HI
st_sf <- shift_geometry(
              st_sf,
              geoid_column = NULL,
              preserve_area = FALSE,
              position = c("below", "outside")
            )

Code

# Join our NMTC projects data with our shapefile geocoordinates
svi_national_county_nmtc_sf <- left_join(svi_national_county_nmtc_projects, county_sf, join_by("FIPS_st" == "STATEFP", "FIPS_county" == "COUNTYFP"))

svi_national_county_nmtc_sf %>% head(5) %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

State	County	Division	post10_nmtc_project_cnt	tract_cnt	post10_nmtc_project_dollars	post10_nmtc_dollars_formatted	fips_county_st	FIPS_st	FIPS_county	state_name	region_number	region	division_number	flag_count10	pop10	flag_by_pop10	flag_count_quantile10	flag_pop_quantile10	flag_count20	pop20	flag_by_pop20	flag_count_quantile20	flag_pop_quantile20	county_name	GEO_ID	STATE	COUNTY	NAME	LSAD	CENSUSAREA	geometry
AK	Aleutians East Borough	Pacific Division	1	1	15762500	$15,762,500	02013	02	013	Alaska	4	West Region	9	8	3703	0.0021604	0.4	1.0	5	3389	0.0014754	0.2	0.8	Aleutians East Borough, AK	0500000US02013	02	013	Aleutians East	Borough	6981.943	MULTIPOLYGON (((-2385249 -1...
AK	Anchorage Municipality	Pacific Division	1	13	9800000	$9,800,000	02020	02	020	Alaska	4	West Region	9	72	64432	0.0011175	1.0	0.4	87	69679	0.0012486	1.0	0.6	Anchorage Municipality, AK	0500000US02020	02	020	Anchorage	Muny	1704.683	MULTIPOLYGON (((-1927463 -1...
AK	Wade Hampton Census Area	Pacific Division	1	1	21420000	$21,420,000	02270	02	270	Alaska	4	West Region	9	9	7398	0.0012165	0.4	0.6	10	8298	0.0012051	0.4	0.6	Wade Hampton Census Area, AK	0500000US02270	02	270	Wade Hampton	CA	17081.433	MULTIPOLYGON (((-2310112 -1...
AK	Yukon-Koyukuk Census Area	Pacific Division	1	3	7644000	$7,644,000	02290	02	290	Alaska	4	West Region	9	27	4027	0.0067047	0.8	1.0	31	3979	0.0077909	0.8	1.0	Yukon-Koyukuk Census Area, AK	0500000US02290	02	290	Yukon-Koyukuk	CA	145504.789	MULTIPOLYGON (((-1736112 -9...
AL	Baldwin County	East South Central Division	4	8	17268000	$17,268,000	01003	01	003	Alabama	3	South Region	6	34	38458	0.0008841	0.8	0.4	34	46255	0.0007351	0.8	0.2	Baldwin County, AL	0500000US01003	01	003	Baldwin	County	1589.784	MULTIPOLYGON (((820813.4 -7...

Code

# Create classes for bivariate mapping 
svi_national_county_nmtc_sf <- bi_class(svi_national_county_nmtc_sf, x = flag_count10, y = post10_nmtc_project_dollars, style = "quantile", dim = 3)

# View data
svi_national_county_nmtc_sf %>% head(5) %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

State	County	Division	post10_nmtc_project_cnt	tract_cnt	post10_nmtc_project_dollars	post10_nmtc_dollars_formatted	fips_county_st	FIPS_st	FIPS_county	state_name	region_number	region	division_number	flag_count10	pop10	flag_by_pop10	flag_count_quantile10	flag_pop_quantile10	flag_count20	pop20	flag_by_pop20	flag_count_quantile20	flag_pop_quantile20	county_name	GEO_ID	STATE	COUNTY	NAME	LSAD	CENSUSAREA	geometry	bi_class
AK	Aleutians East Borough	Pacific Division	1	1	15762500	$15,762,500	02013	02	013	Alaska	4	West Region	9	8	3703	0.0021604	0.4	1.0	5	3389	0.0014754	0.2	0.8	Aleutians East Borough, AK	0500000US02013	02	013	Aleutians East	Borough	6981.943	MULTIPOLYGON (((-2385249 -1...	1-2
AK	Anchorage Municipality	Pacific Division	1	13	9800000	$9,800,000	02020	02	020	Alaska	4	West Region	9	72	64432	0.0011175	1.0	0.4	87	69679	0.0012486	1.0	0.6	Anchorage Municipality, AK	0500000US02020	02	020	Anchorage	Muny	1704.683	MULTIPOLYGON (((-1927463 -1...	2-2
AK	Wade Hampton Census Area	Pacific Division	1	1	21420000	$21,420,000	02270	02	270	Alaska	4	West Region	9	9	7398	0.0012165	0.4	0.6	10	8298	0.0012051	0.4	0.6	Wade Hampton Census Area, AK	0500000US02270	02	270	Wade Hampton	CA	17081.433	MULTIPOLYGON (((-2310112 -1...	1-3
AK	Yukon-Koyukuk Census Area	Pacific Division	1	3	7644000	$7,644,000	02290	02	290	Alaska	4	West Region	9	27	4027	0.0067047	0.8	1.0	31	3979	0.0077909	0.8	1.0	Yukon-Koyukuk Census Area, AK	0500000US02290	02	290	Yukon-Koyukuk	CA	145504.789	MULTIPOLYGON (((-1736112 -9...	2-1
AL	Baldwin County	East South Central Division	4	8	17268000	$17,268,000	01003	01	003	Alabama	3	South Region	6	34	38458	0.0008841	0.8	0.4	34	46255	0.0007351	0.8	0.2	Baldwin County, AL	0500000US01003	01	003	Baldwin	County	1589.784	MULTIPOLYGON (((820813.4 -7...	2-2

Finally we can create our map:

Code

# Create map with ggplot
svi_national_county_nmtc_map <- ggplot() +
  # Map county shapefile, fill with bi_class categories
  geom_sf(data = svi_national_county_nmtc_sf, mapping = aes(geometry=geometry, fill = bi_class), color = "white", size = 0.1, show.legend = FALSE) +
  # Set to biscale palette
  bi_scale_fill(pal = "GrPink", dim = 3) +
  # Add state shapefiles for outline
  geom_sf(data=st_sf, color="black", fill=NA, linewidth=.5, aes(geometry=geometry)) +
  labs(
    title = "Correlation of 2010 National SVI Flag Count and 2011 - 2020 NMTC Tax Dollars",
  ) +
  # Set them to biscale
  bi_theme(base_size = 10)

# Create biscale legend
svi_national_county_nmtc_legend <- bi_legend(pal = "GrPink",
                    dim = 3,
                    xlab = "SVI Flag Count",
                    ylab = "NMTC Dollars",
                    size = 8)

# Combine map with legend using cowplot
svi_national_county_nmtc_bivarmap <- ggdraw() +
  draw_plot(svi_national_county_nmtc_map) +
  # Set legend location
  draw_plot(svi_national_county_nmtc_legend, x= -.02,  y = -.05,
 width=.20)


# View map
svi_national_county_nmtc_bivarmap

Here we can see the distribution of our counties with NMTC projects based on the correlation between 2010 SVI Flag Count and NMTC dollars.

For example, we can see several counties in WI have moderate-to-high amounts of NMTC dollars even though they have relatively low SVI amounts:

Code

svi_national_county_nmtc_sf %>% filter(State == "WI") %>% select(State, County, flag_count10, post10_nmtc_dollars_formatted) %>% arrange(desc(flag_count10)) %>% head(6)

  State           County flag_count10 post10_nmtc_dollars_formatted
1    WI Milwaukee County          984                  $315,495,493
2    WI     Brown County           82                   $22,110,000
3    WI      Dane County           74                   $46,498,037
4    WI      Rock County           72                   $29,580,000
5    WI   Kenosha County           61                   $36,800,000
6    WI Sheboygan County           26                    $7,305,000

PA has a cluster of counties with moderate-to-high SVI flag counts and corresponding moderate-to-high NMTC dollar amounts:

Code

svi_national_county_nmtc_sf %>% filter(State == "PA") %>% select(State, County, flag_count10, post10_nmtc_dollars_formatted) %>% arrange(desc(flag_count10)) %>% head(6)

  State              County flag_count10 post10_nmtc_dollars_formatted
1    PA Philadelphia County         1906                  $550,969,964
2    PA    Allegheny County          731                  $244,342,400
3    PA     Delaware County          235                   $14,190,000
4    PA        Berks County          225                    $7,840,000
5    PA         Erie County          178                    $7,358,392
6    PA      Dauphin County          137                   $32,123,500

Arizona has several high SVI Flag and high NMTC dollar counties and a moderate SVI Flag, low NMTC dollar county:

Code

svi_national_county_nmtc_sf %>% filter(State == "AZ") %>% select(State, County, flag_count10, post10_nmtc_dollars_formatted) %>% arrange(desc(flag_count10)) %>% head(6)

  State          County flag_count10 post10_nmtc_dollars_formatted
1    AZ Maricopa County         2453                   $84,923,464
2    AZ     Pima County          728                   $36,122,128
3    AZ     Yuma County          276                    $1,454,000
4    AZ    Pinal County          203                   $37,224,559
5    AZ   Navajo County          189                   $46,134,750
6    AZ   Apache County          129                   $12,544,000

LIHTC

Correlation between outcome & intervention

We can now repeat our analysis for the LIHTC to identify if there is a relationship between dollars counties received from this program .

Recall that we will want to review our summary statistics, a scatterplot, and a calculation of Pearson’s r to measure the correlation.

First let’s create a dataset of only counties with LIHTC projects:

Code

svi_national_county_lihtc_projects <- svi_national_county_lihtc %>% filter(post10_lihtc_project_cnt > 0)

Now let’s review the summary statistics for our data set:

Code

summary(svi_national_county_lihtc_projects$flag_count10)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
    0.0    17.0    33.0   104.6   113.5  2457.0

Code

summary(svi_national_county_lihtc_projects$post10_lihtc_project_dollars)

    Min.  1st Qu.   Median     Mean  3rd Qu.     Max. 
       0   368649   833390  2747385  2597486 50547731

Note that unlike the NMTC program, there are instances where there are tracts with LIHTC projects, but they did not receive any funding. We want to filter these out of our data set for the purposes of our analysis of the relationship between LIHTC dollars and the SVI flags.

Code

svi_national_county_lihtc_projects <- svi_national_county_lihtc_projects %>% filter(post10_lihtc_project_dollars > 0)

Now we can view the updated summaries:

Code

summary(svi_national_county_lihtc_projects$flag_count10)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
    0.0    17.0    34.0   109.8   112.5  2457.0

Code

summary(svi_national_county_lihtc_projects$post10_lihtc_project_dollars)

    Min.  1st Qu.   Median     Mean  3rd Qu.     Max. 
   56314   605483  1275416  3233901  3424308 50547731

Much like the NMTC program, there’s quite a spread of values. Once again, the minimum flag count for the LIHTC program is 0, however the maximum is only 2,457 compared to over 9,000 for NMTC. The LIHTC dollar amount range is narrower, but starts much higher from ~$56,000 in tax credits to nearly ~$51 million. Once again, let’s view this visually in a scatterplot:

Code

# Scatterplot
# y is our independent variable (LIHTC Project Dollars),  
# x is our dependent variable (SVI flag count)
ggplot2::ggplot(svi_national_county_lihtc_projects,
                aes(x=flag_count10,
                    y=post10_lihtc_project_dollars)) +
        geom_point() +
        geom_smooth(method="lm") +
        scale_y_continuous(labels = scales::dollar_format())

Code

# Pearson's r calculation
cor(svi_national_county_lihtc_projects$flag_count10, svi_national_county_lihtc_projects$post10_lihtc_project_dollars, method = "pearson")

[1] 0.7368838

Similar to the NMTC, we can see that when we consider ALL counties, we have a strong positive correlation between SVI Flag Counts in 2010 and and LIHTC dollars from 2011-2020, suggesting that counties that had more social vulnerability in 2010 received more LIHTC dollars in 2011-2020.

However, once again, we can also see that our data is not in a continuous line. In fact, we appear to have a few more clusters in the LIHTC program data than we had for the NMTC.

The bulk of our data points are once again clustered in the bottom left corner. We have a few more clusters above those and then a single data point all the way in the top right of our plot.

We can use a box plot to look closer at this:

Code

boxplot(svi_national_county_lihtc_projects$flag_count10)

Code

boxplot.stats(svi_national_county_lihtc_projects$flag_count10)$out %>% sort(decreasing = TRUE)

 [1] 2457 1254 1135 1002  835  560  475  440  418  403  402  340  327  323  303
[16]  296  293  276  271  263

This is our same influential point from Los Angeles County, CA:

Code

svi_national_county_lihtc_projects %>% filter(flag_count10 == 2457)

  State             County         Division post10_lihtc_project_cnt tract_cnt
1    CA Los Angeles County Pacific Division                       58       238
  post10_lihtc_project_dollars post10_lihtc_dollars_formatted fips_county_st
1                     50547731                    $50,547,731          06037
  FIPS_st FIPS_county state_name region_number      region division_number
1      06         037 California             4 West Region               9
  flag_count10  pop10 flag_by_pop10 flag_count_quantile10 flag_pop_quantile10
1         2457 988225   0.002486276                     1                 0.6
  flag_count20  pop20 flag_by_pop20 flag_count_quantile20 flag_pop_quantile20
1         2272 991036    0.00229255                     1                 0.6
             county_name
1 Los Angeles County, CA

Code

svi_national_lihtc %>% filter(county == "Los Angeles County") %>% select(GEOID_2010_trt, F_TOTAL_10, post10_lihtc_project_dollars) %>% summary()

 GEOID_2010_trt       F_TOTAL_10    post10_lihtc_project_dollars
 Length:238         Min.   : 6.00   Min.   :      0             
 Class :character   1st Qu.:10.00   1st Qu.:      0             
 Mode  :character   Median :10.00   Median :      0             
                    Mean   :10.32   Mean   : 212385             
                    3rd Qu.:11.00   3rd Qu.:      0             
                    Max.   :13.00   Max.   :4945372

Looking at the summary stats for LA County, we can again quickly conclude that we have not made an error in our calculations, there are indeed 238 tracts in our Los Angeles County data set and with a median total SVI Flag count (at top 25% vulnerability) of 10 per tract and a max of 13 per tract, it’s reasonable to have ~2500 flags.

Code

238*10

[1] 2380

Code

238*13

[1] 3094

Similarly, the max tract has $4,945,372 LIHTC dollars while the mean tract has $212,385 dollars.

Therefore, we can conclude that there is no reason to exclude LA County from our national analysis of the relationship between SVI Flag Counts in 2010 and LIHTC Dollars from 2011-2020.

Now recall from our NMTC analysis that we can utilize an algorithm known as k-means clustering to create clusters within our data set and examine each of the groupings separately.

K-Means Clustering

Once again, we first need to create a dataset of just our variables of interest and set our county_name column to the rownames since only numeric values can be entered into the kmeans() function.

We also want to double-check that all null values are absent from the data set and use scale() to convert our data to a comparable range:

Code

svi_national_lihtc_cluster <- svi_national_county_lihtc_projects %>% 
                            select(county_name, post10_lihtc_project_dollars, 
                                   flag_count10) %>% 
                            remove_rownames %>% 
                            column_to_rownames(var="county_name")

# Remove nulls, if in dataset
svi_national_lihtc_cluster <- na.omit(svi_national_lihtc_cluster)


# Scale numeric variables
svi_national_lihtc_cluster <- scale(svi_national_lihtc_cluster)


svi_national_lihtc_cluster %>% head(5)

                     post10_lihtc_project_dollars flag_count10
Dale County, AL                        -0.4426510   -0.4100636
Mobile County, AL                      -0.4215575    0.1570056
Craighead County, AR                   -0.1126573   -0.4100636
Jefferson County, AR                   -0.4806216   -0.2744601
Pope County, AR                        -0.4860654   -0.4265004

Next we can try a few different cluster numbers and allow the algorithm to search through 25 sets to identify the best groupings for each number:

Code

set.seed(123)
k2_lihtc_nat <- kmeans(svi_national_lihtc_cluster, centers = 2, nstart = 25)
set.seed(123)
k3_lihtc_nat <- kmeans(svi_national_lihtc_cluster, centers = 3, nstart = 25)
set.seed(123)
k4_lihtc_nat <- kmeans(svi_national_lihtc_cluster, centers = 4, nstart = 25)
set.seed(123)
k5_lihtc_nat <- kmeans(svi_national_lihtc_cluster, centers = 5, nstart = 25)

Next we can view the plots to visually check the groupings and see if there’s any overlap:

Code

# plots to compare
p_k2_lihtc_nat <- factoextra::fviz_cluster(k2_lihtc_nat, geom = "point", data = svi_national_lihtc_cluster) + ggtitle("k = 2")

p_k3_lihtc_nat <- factoextra::fviz_cluster(k3_lihtc_nat, geom = "point", data = svi_national_lihtc_cluster) + ggtitle("k = 3")

p_k4_lihtc_nat <- factoextra::fviz_cluster(k4_lihtc_nat, geom = "point",  data = svi_national_lihtc_cluster) + ggtitle("k = 4")

p_k5_lihtc_nat <- factoextra::fviz_cluster(k5_lihtc_nat, geom = "point",  data = svi_national_lihtc_cluster) + ggtitle("k = 5")

grid.arrange(p_k2_lihtc_nat, p_k3_lihtc_nat, p_k4_lihtc_nat, p_k5_lihtc_nat, nrow = 2)

Once more visually group counts 3 and 4 appear to provide the best options without too much overlap.

However, we’ll run our Elbow Plot function again to confirm:

Code

elbow_plot(svi_national_lihtc_cluster)

[1] 1
[1] 2
[1] 3
[1] 4
[1] 5
[1] 6
[1] 7
[1] 8
[1] 9
[1] 10
[1] 11
[1] 12
[1] 13
[1] 14
[1] 15

Here we can see that the spacing between clusters decreases substantially after 3. Thus, we will go with 3 clusters again:

Code

p_k3_lihtc_nat <- factoextra::fviz_cluster(k3_lihtc_nat, geom = "point", data = svi_national_lihtc_cluster) + ggtitle("k = 3")

p_k3_lihtc_nat

We can then transform our cluster matrix back to a data frame and assign these clusters to our counties:

Code

svi_national_lihtc_cluster_label <- as.data.frame(svi_national_lihtc_cluster) %>%
                                  rownames_to_column(var = "county_name") %>%
                                  as_tibble() %>%
                                  mutate(cluster = k3_lihtc_nat$cluster) %>%
                                  select(county_name, cluster)

svi_national_county_lihtc_projects2 <- left_join(svi_national_county_lihtc_projects, svi_national_lihtc_cluster_label, join_by(county_name == county_name))

# View county counts in each cluster
table(svi_national_county_lihtc_projects2$cluster)


  1   2   3 
164  27   1

Now we can re-examine the correlation between 2010 SVI Flag Counts and LIHTC Project Dollars for each subset of our data.

First recall our overall outcomes:

Code

# Overall Scatterplot
# y is our independent variable (LIHTC Project Dollars),  
# x is our dependent variable (SVI flag count)
ggplot2::ggplot(svi_national_county_lihtc_projects2,
                aes(x=flag_count10,
                    y=post10_lihtc_project_dollars)) +
        geom_point() +
        geom_smooth(method="lm") +
        scale_y_continuous(labels = scales::dollar_format())

Code

# Pearson's r calculation
cor(svi_national_county_lihtc_projects2$flag_count10, svi_national_county_lihtc_projects2$post10_lihtc_project_dollars, method = "pearson")

[1] 0.7368838

Now let’s look at our lower end counties in cluster 1 (bottom left corner):

Code

# Cluster 1 Scatterplot
# y is our independent variable (LIHTC Project Dollars),  
# x is our dependent variable (SVI flag count)

svi_national_county_lihtc_projects2 %>% 
  filter(cluster == 1) %>%
  ggplot2::ggplot(aes(x=flag_count10,
                    y=post10_lihtc_project_dollars)) +
        geom_point() +
        geom_smooth(method="lm") +
        scale_y_continuous(labels = scales::dollar_format())

Code

svi_national_county_lihtc_projects2 %>% 
  filter(cluster == 1) %>%
  select(flag_count10,post10_lihtc_project_dollars) %>%
  cor(method = "pearson")

                             flag_count10 post10_lihtc_project_dollars
flag_count10                    1.0000000                    0.2812405
post10_lihtc_project_dollars    0.2812405                    1.0000000

Here we can see our correlation has dropped from strong to weak. As we can see, there are still several sub-clusters in our data. Thus, we can confirm that LA County has a strong influence on our correlation.

We can also conclude that there may not be as strong of a relationship between SVI Flags and the LIHTC dollars. This could partly be because the LIHTC credit program is meant to target low income households, but is not as tied to low income communities as the NMTC.

We can see some of these cluster 1 counties here:

Code

svi_national_county_lihtc_projects2 %>% 
  filter(cluster == 1) %>%
  select(county_name, flag_count10, post10_lihtc_dollars_formatted) %>%
  arrange(desc(flag_count10)) %>% head(10) %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

county_name	flag_count10	post10_lihtc_dollars_formatted
Queens County, NY	296	$4,094,899
Oklahoma County, OK	293	$590,000
Orleans Parish, LA	276	$3,558,074
Sacramento County, CA	207	$4,065,883
Passaic County, NJ	206	$4,564,679
Hartford County, CT	203	$256,961
Alameda County, CA	202	$1,590,984
Erie County, NY	167	$2,220,667
Shelby County, TN	167	$201,735
Monroe County, NY	165	$4,944,903

Now let’s examine our mid-range points in Cluster 2:

Code

# Cluster 2 Scatterplot
# y is our independent variable (LIHTC Project Dollars),  
# x is our dependent variable (SVI flag count)

svi_national_county_lihtc_projects2 %>% 
  filter(cluster == 2) %>%
  ggplot2::ggplot(aes(x=flag_count10,
                    y=post10_lihtc_project_dollars)) +
        geom_point() +
        geom_smooth(method="lm") +
        scale_y_continuous(labels = scales::dollar_format())

Code

svi_national_county_lihtc_projects2 %>% 
  filter(cluster == 2) %>%
  select(flag_count10,post10_lihtc_project_dollars) %>%
  cor(method = "pearson")

                             flag_count10 post10_lihtc_project_dollars
flag_count10                   1.00000000                  -0.02464747
post10_lihtc_project_dollars  -0.02464747                   1.00000000

Again, our mid range points are scattered and have a very weak correlation that skews slightly negative, but doesn’t have enough strength for us to confidently draw conclusions.

Rather, it seems the amount of money given to counties with 0 - 1250 SVI flags varied widely between less than $10 million to over $20 million.

We can view these counties here:

Code

svi_national_county_lihtc_projects2 %>% 
  filter(cluster == 2) %>%
  select(county_name, flag_count10, post10_lihtc_dollars_formatted) %>%
  arrange(desc(flag_count10)) %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

county_name	flag_count10	post10_lihtc_dollars_formatted
Cook County, IL	1254	$6,872,376
Kings County, NY	1135	$26,054,976
Wayne County, MI	1002	$11,226,253
Harris County, TX	835	$179,539
Essex County, NJ	560	$7,410,996
Maricopa County, AZ	475	$13,115,292
Bronx County, NY	440	$19,909,800
Cuyahoga County, OH	418	$4,515,742
District of Columbia, DC	403	$11,695,555
San Diego County, CA	402	$20,961,962
Milwaukee County, WI	340	$11,454,416
Baltimore city, MD	327	$6,501,415
Orange County, CA	323	$10,245,926
Miami-Dade County, FL	303	$12,039,478
Riverside County, CA	271	$6,335,483
San Bernardino County, CA	263	$5,757,810
Philadelphia County, PA	253	$6,805,843
New York County, NY	202	$9,337,368
Allegheny County, PA	191	$8,889,633
Hennepin County, MN	178	$8,327,899
Onondaga County, NY	152	$18,599,402
Tulsa County, OK	146	$8,175,983
Hillsborough County, FL	143	$10,116,734
San Francisco County, CA	79	$11,194,380
Delaware County, IN	31	$17,000,000
Vigo County, IN	22	$18,646,385
Mesa County, CO	13	$15,437,500

Finally, let’s look at our cluster 3 data (top right corner):

Code

# Cluster 3 Scatterplot
# y is our independent variable (LIHTC Project Dollars),  
# x is our dependent variable (SVI flag count)

svi_national_county_lihtc_projects2 %>% 
  filter(cluster == 3) %>%
  ggplot2::ggplot(aes(x=flag_count10,
                    y=post10_lihtc_project_dollars)) +
        geom_point() +
        geom_smooth(method="lm") +
        scale_y_continuous(labels = scales::dollar_format())

Code

svi_national_county_lihtc_projects2 %>% 
  filter(cluster == 3) %>%
  select(flag_count10,post10_lihtc_project_dollars) %>%
  cor(method = "pearson")

                             flag_count10 post10_lihtc_project_dollars
flag_count10                           NA                           NA
post10_lihtc_project_dollars           NA                           NA

Since there is only 1 point, we can’t calculate a correlation, but we can confirm that this point is LA County:

Code

svi_national_county_lihtc_projects2 %>% 
  filter(cluster == 3) %>%
  select(county_name, flag_count10, post10_lihtc_dollars_formatted) %>% 
  arrange(desc(flag_count10)) %>% head(10) %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

county_name	flag_count10	post10_lihtc_dollars_formatted
Los Angeles County, CA	2457	$50,547,731

Bivariate Map

Now let’s view this relationship spatially by creating another bivariate map:

Code

# Join our LIHTC projects data with our shapefile geocoordinates
svi_national_county_lihtc_sf <- left_join(svi_national_county_lihtc_projects, county_sf, join_by("FIPS_st" == "STATEFP", "FIPS_county" == "COUNTYFP"))

svi_national_county_lihtc_sf %>% head(5) %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

State	County	Division	post10_lihtc_project_cnt	tract_cnt	post10_lihtc_project_dollars	post10_lihtc_dollars_formatted	fips_county_st	FIPS_st	FIPS_county	state_name	region_number	region	division_number	flag_count10	pop10	flag_by_pop10	flag_count_quantile10	flag_pop_quantile10	flag_count20	pop20	flag_by_pop20	flag_count_quantile20	flag_pop_quantile20	county_name	GEO_ID	STATE	COUNTY	NAME	LSAD	CENSUSAREA	geometry
AL	Dale County	East South Central Division	1	2	801670	$801,670	01045	01	045	Alabama	3	South Region	6	10	4943	0.0020231	0.4	0.4	15	4853	0.0030909	0.6	0.8	Dale County, AL	0500000US01045	01	045	Dale	County	561.150	MULTIPOLYGON (((966402.4 -6...
AL	Mobile County	East South Central Division	1	18	917572	$917,572	01097	01	097	Alabama	3	South Region	6	148	41977	0.0035257	1.0	0.8	126	34483	0.0036540	1.0	0.8	Mobile County, AL	0500000US01097	01	097	Mobile	County	1229.435	MULTIPOLYGON (((763284.2 -7...
AR	Craighead County	West South Central Division	6	1	2614884	$2,614,884	05031	05	031	Arkansas	3	South Region	7	10	5701	0.0017541	0.4	0.4	9	6088	0.0014783	0.4	0.2	Craighead County, AR	0500000US05031	05	031	Craighead	County	707.206	MULTIPOLYGON (((509938.5 -1...
AR	Jefferson County	West South Central Division	1	5	593033	$593,033	05069	05	069	Arkansas	3	South Region	7	43	14174	0.0030337	1.0	0.8	39	11370	0.0034301	0.8	0.8	Jefferson County, AR	0500000US05069	05	069	Jefferson	County	870.746	MULTIPOLYGON (((391413.8 -3...
AR	Pope County	West South Central Division	1	1	563121	$563,121	05115	05	115	Arkansas	3	South Region	7	6	4220	0.0014218	0.2	0.2	9	4890	0.0018405	0.4	0.4	Pope County, AR	0500000US05115	05	115	Pope	County	812.548	MULTIPOLYGON (((243262.7 -2...

Code

# Create classes for bivariate mapping 
svi_national_county_lihtc_sf <- bi_class(svi_national_county_lihtc_sf, x = flag_count10, y = post10_lihtc_project_dollars, style = "quantile", dim = 3)

# View data
svi_national_county_lihtc_sf %>% head(5) %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

State	County	Division	post10_lihtc_project_cnt	tract_cnt	post10_lihtc_project_dollars	post10_lihtc_dollars_formatted	fips_county_st	FIPS_st	FIPS_county	state_name	region_number	region	division_number	flag_count10	pop10	flag_by_pop10	flag_count_quantile10	flag_pop_quantile10	flag_count20	pop20	flag_by_pop20	flag_count_quantile20	flag_pop_quantile20	county_name	GEO_ID	STATE	COUNTY	NAME	LSAD	CENSUSAREA	geometry	bi_class
AL	Dale County	East South Central Division	1	2	801670	$801,670	01045	01	045	Alabama	3	South Region	6	10	4943	0.0020231	0.4	0.4	15	4853	0.0030909	0.6	0.8	Dale County, AL	0500000US01045	01	045	Dale	County	561.150	MULTIPOLYGON (((966402.4 -6...	1-2
AL	Mobile County	East South Central Division	1	18	917572	$917,572	01097	01	097	Alabama	3	South Region	6	148	41977	0.0035257	1.0	0.8	126	34483	0.0036540	1.0	0.8	Mobile County, AL	0500000US01097	01	097	Mobile	County	1229.435	MULTIPOLYGON (((763284.2 -7...	3-2
AR	Craighead County	West South Central Division	6	1	2614884	$2,614,884	05031	05	031	Arkansas	3	South Region	7	10	5701	0.0017541	0.4	0.4	9	6088	0.0014783	0.4	0.2	Craighead County, AR	0500000US05031	05	031	Craighead	County	707.206	MULTIPOLYGON (((509938.5 -1...	1-3
AR	Jefferson County	West South Central Division	1	5	593033	$593,033	05069	05	069	Arkansas	3	South Region	7	43	14174	0.0030337	1.0	0.8	39	11370	0.0034301	0.8	0.8	Jefferson County, AR	0500000US05069	05	069	Jefferson	County	870.746	MULTIPOLYGON (((391413.8 -3...	2-1
AR	Pope County	West South Central Division	1	1	563121	$563,121	05115	05	115	Arkansas	3	South Region	7	6	4220	0.0014218	0.2	0.2	9	4890	0.0018405	0.4	0.4	Pope County, AR	0500000US05115	05	115	Pope	County	812.548	MULTIPOLYGON (((243262.7 -2...	1-1

Finally we can create our map:

Code

# Create map with ggplot
svi_national_county_lihtc_map <- ggplot() +
  # Map county shapefile, fill with bi_class categories
  geom_sf(data = svi_national_county_lihtc_sf, mapping = aes(geometry=geometry, fill = bi_class), color = "white", size = 0.1, show.legend = FALSE) +
  # Set to biscale palette
  bi_scale_fill(pal = "GrPink", dim = 3) +
  # Add state shapefiles for outline
  geom_sf(data=st_sf, color="black", fill=NA, linewidth=.5, aes(geometry=geometry)) +
  labs(
    title = "Correlation of 2010 National SVI Flag Count and 2011 - 2020 LIHTC Tax Dollars",
  ) +
  # Set them to biscale
  bi_theme(base_size = 10)

# Create biscale legend
svi_national_county_lihtc_legend <- bi_legend(pal = "GrPink",
                    dim = 3,
                    xlab = "SVI Flag Count",
                    ylab = "LIHTC Dollars",
                    size = 8)

# Combine map with legend using cowplot
svi_national_county_lihtc_bivarmap <- ggdraw() +
  draw_plot(svi_national_county_lihtc_map) +
  # Set legend location
  draw_plot(svi_national_county_lihtc_legend, x= -.02,  y = -.05,
 width=.20)


# View map
svi_national_county_lihtc_bivarmap

Here we can see the distribution of our LIHTC counties is quite a bit less than our NMTC projects. However, we can once again review the correlation between 2010 SVI Flag Count and LIHTC dollars.

For example, we can see a few counties in CO that have moderate-to-high amounts of LIHTC dollars even though they have relatively low SVI flag counts:

Code

svi_national_county_lihtc_sf %>% filter(State == "CO") %>% select(State, County, flag_count10, post10_lihtc_dollars_formatted) %>% arrange(desc(flag_count10)) %>% head(6)

  State         County flag_count10 post10_lihtc_dollars_formatted
1    CO  Denver County           69                     $5,226,128
2    CO El Paso County           18                     $1,011,891
3    CO Larimer County           17                     $2,609,648
4    CO    Mesa County           13                    $15,437,500

CA has a cluster of counties with moderate-to-high SVI flag counts and corresponding moderate-to-high LIHTC dollar amounts:

Code

svi_national_county_lihtc_sf %>% filter(State == "CA") %>% select(State, County, flag_count10, post10_lihtc_dollars_formatted) %>% arrange(desc(flag_count10)) %>% head(6)

  State                County flag_count10 post10_lihtc_dollars_formatted
1    CA    Los Angeles County         2457                    $50,547,731
2    CA      San Diego County          402                    $20,961,962
3    CA         Orange County          323                    $10,245,926
4    CA      Riverside County          271                     $6,335,483
5    CA San Bernardino County          263                     $5,757,810
6    CA     Sacramento County          207                     $4,065,883

Divisional Exploratory Data Analysis: Visualizing The Intervention

Now that we have done a walk-through of the national trends of the NMTC and LIHTC data, let’s zone into our census division:

NMTC

Correlation between outcome & intervention

Create projects df:

Code

svi_divisional_county_nmtc_projects <- svi_divisional_county_nmtc %>% filter(post10_nmtc_project_cnt > 0)

Check that our expected division is loaded:

Code

svi_divisional_county_nmtc_projects %>% select(Division) %>% unique()

                  Division
1 Middle Atlantic Division

Now let’s review the summary statistics for our data set:

Code

summary(svi_divisional_county_nmtc_projects$flag_count10)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
   5.00   54.75  134.50  399.71  346.00 3869.00

Code

summary(svi_divisional_county_nmtc_projects$post10_nmtc_project_dollars)

     Min.   1st Qu.    Median      Mean   3rd Qu.      Max. 
  1460000   7800000  16225000  51968192  41860000 550969964

As we can see from the summary statistics, there’s also quite a spread of values across counties in the Middle Atlantic Division from 5 SVI flags to over 3,800 and ~$1.5 million in tax credits to over $.5bn. Let’s view this visually in a scatterplot:

Code

# Scatterplot
# y is our independent variable (NMTC Project Dollars),  
# x is our dependent variable (SVI flag count)
ggplot2::ggplot(svi_divisional_county_nmtc_projects,
                aes(x=flag_count10,
                    y=post10_nmtc_project_dollars)) +
        geom_point() +
        geom_smooth(method="lm") +
        scale_y_continuous(labels = scales::dollar_format())

Code

# Pearson's r calculation
cor(svi_divisional_county_nmtc_projects$flag_count10, svi_divisional_county_nmtc_projects$post10_nmtc_project_dollars, method = "pearson")

[1] 0.7085789

Here we have a similar pattern to the national data, though the top right outlier is not quite as extreme.

We have a strong positive correlation between SVI Flag Counts in 2010, suggesting that counties that had more social vulnerability in 2010 received more NMTC tax credit dollars in 2011-2020.

However, our data is not in a perfect, continuous line. Rather, we have the majority of our data clustered in the bottom left corner and some scatter across the plot.

We can use a box plot to look closer at this:

Code

boxplot(svi_divisional_county_nmtc_projects$flag_count10)

Code

boxplot.stats(svi_divisional_county_nmtc_projects$flag_count10)$out %>% sort(decreasing = TRUE)

[1] 3869 2688 2347 1961 1019  879  841

While our 7 outliers are closer together, we can still see that our county with 3,869 has over 1,000 more SVI flags than the next county:

We can filter our data set to identify these:

Code

svi_divisional_county_nmtc_projects %>% 
  select(county_name, flag_count10, post10_nmtc_dollars_formatted) %>% 
  arrange(desc(flag_count10)) %>% 
  head(7) %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

county_name	flag_count10	post10_nmtc_dollars_formatted
Kings County, NY	3869	$216,348,600
Bronx County, NY	2688	$306,355,715
Queens County, NY	2347	$85,225,100
Philadelphia County, PA	1961	$550,969,964
Essex County, NJ	1019	$81,662,084
New York County, NY	879	$255,545,686
Hudson County, NJ	841	$110,136,049

K-Means Clustering

Now let’s examine our divisional data in segments:

Code

svi_divisional_nmtc_cluster <- svi_divisional_county_nmtc_projects %>% 
                            select(county_name, post10_nmtc_project_dollars, 
                                   flag_count10) %>% 
                            remove_rownames %>% 
                            column_to_rownames(var="county_name")

# Remove nulls, if in dataset
svi_divisional_nmtc_cluster <- na.omit(svi_divisional_nmtc_cluster)


# Scale numeric variables
svi_divisional_nmtc_cluster <- scale(svi_divisional_nmtc_cluster)


svi_divisional_nmtc_cluster %>% head(5)

                      post10_nmtc_project_dollars flag_count10
Bergen County, NJ                      -0.4296451   -0.3418568
Camden County, NJ                       0.2835350   -0.0912361
Cumberland County, NJ                  -0.1922645   -0.3526362
Essex County, NJ                        0.3039882    0.8344437
Hudson County, NJ                       0.5954875    0.5946023

Next we can try a few different cluster numbers and allow the algorithm to search through 25 sets to identify the best groupings for each number:

Code

set.seed(123)
k2_nmtc_div <- kmeans(svi_divisional_nmtc_cluster, centers = 2, nstart = 25)
set.seed(123)
k3_nmtc_div <- kmeans(svi_divisional_nmtc_cluster, centers = 3, nstart = 25)
set.seed(123)
k4_nmtc_div <- kmeans(svi_divisional_nmtc_cluster, centers = 4, nstart = 25)
set.seed(123)
k5_nmtc_div <- kmeans(svi_divisional_nmtc_cluster, centers = 5, nstart = 25)

Next we can view the plots to visually check the groupings and see if there’s any overlap:

Code

# plots to compare
p_k2_nmtc_div <- factoextra::fviz_cluster(k2_nmtc_div, geom = "point", data = svi_divisional_nmtc_cluster) + ggtitle("k = 2")

p_k3_nmtc_div <- factoextra::fviz_cluster(k3_nmtc_div, geom = "point", data = svi_divisional_nmtc_cluster) + ggtitle("k = 3")

p_k4_nmtc_div <- factoextra::fviz_cluster(k4_nmtc_div, geom = "point",  data = svi_divisional_nmtc_cluster) + ggtitle("k = 4")

p_k5_nmtc_div <- factoextra::fviz_cluster(k5_nmtc_div, geom = "point",  data = svi_divisional_nmtc_cluster) + ggtitle("k = 5")

grid.arrange(p_k2_nmtc_div, p_k3_nmtc_div, p_k4_nmtc_div, p_k5_nmtc_div, nrow = 2)

Here the 2 grouping appears to be the only one with multiple members across clusters, however we can confirm our visual inspection with our elbow plot:

Code

elbow_plot(svi_divisional_nmtc_cluster)

[1] 1
[1] 2
[1] 3
[1] 4
[1] 5
[1] 6
[1] 7
[1] 8
[1] 9
[1] 10
[1] 11
[1] 12
[1] 13
[1] 14
[1] 15

Here we can see that the spacing between clusters decreases substantially after 2. Thus, we will go with 2 clusters:

Code

p_k2_nmtc_div <- factoextra::fviz_cluster(k2_nmtc_div, geom = "point", data = svi_divisional_nmtc_cluster) + ggtitle("k = 2")

p_k2_nmtc_div

We can then transform our cluster matrix back to a data frame and assign these clusters to our counties:

Code

svi_divisional_nmtc_cluster_label <- as.data.frame(svi_divisional_nmtc_cluster) %>%
                                  rownames_to_column(var = "county_name") %>%
                                  as_tibble() %>%
                                  mutate(cluster = k2_nmtc_div$cluster) %>%
                                  select(county_name, cluster)

svi_divisional_county_nmtc_projects2 <- left_join(svi_divisional_county_nmtc_projects, svi_divisional_nmtc_cluster_label, join_by(county_name == county_name))

# View county counts in each cluster
table(svi_divisional_county_nmtc_projects2$cluster)


 1  2 
 6 46

Now we can re-examine the correlation between 2010 SVI Flag Counts and NMTC Project Dollars for each subset of our data.

First recall our overall outcomes:

Code

# Overall Scatterplot
# y is our independent variable (NMTC Project Dollars),  
# x is our dependent variable (SVI flag count)
ggplot2::ggplot(svi_divisional_county_nmtc_projects2,
                aes(x=flag_count10,
                    y=post10_nmtc_project_dollars)) +
        geom_point() +
        geom_smooth(method="lm") +
        scale_y_continuous(labels = scales::dollar_format())

Code

# Pearson's r calculation
cor(svi_divisional_county_nmtc_projects2$flag_count10, svi_divisional_county_nmtc_projects2$post10_nmtc_project_dollars, method = "pearson")

[1] 0.7085789

Now let’s look at our smaller cluster of points in Cluster 1:

Code

# Cluster 1 Scatterplot
# y is our independent variable (NMTC Project Dollars),  
# x is our dependent variable (SVI flag count)

svi_divisional_county_nmtc_projects2 %>% 
  filter(cluster == 1) %>%
  ggplot2::ggplot(aes(x=flag_count10,
                    y=post10_nmtc_project_dollars)) +
        geom_point() +
        geom_smooth(method="lm") +
        scale_y_continuous(labels = scales::dollar_format())

Code

svi_divisional_county_nmtc_projects2 %>% 
  filter(cluster == 1) %>%
  select(flag_count10,post10_nmtc_project_dollars) %>%
  cor(method = "pearson")

                            flag_count10 post10_nmtc_project_dollars
flag_count10                    1.000000                   -0.114767
post10_nmtc_project_dollars    -0.114767                    1.000000

Here we can see that our highest data points have a very weak slightly negative to none-existent correlation on their own. Most of our counties with ~1,000 to 4,000 flags have similar amounts of NMTC dollars:

We can view these counties here:

Code

svi_divisional_county_nmtc_projects2 %>% 
  filter(cluster == 1) %>%
  select(county_name, flag_count10, post10_nmtc_dollars_formatted) %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

county_name	flag_count10	post10_nmtc_dollars_formatted
Bronx County, NY	2688	$306,355,715
Kings County, NY	3869	$216,348,600
New York County, NY	879	$255,545,686
Queens County, NY	2347	$85,225,100
Allegheny County, PA	712	$244,342,400
Philadelphia County, PA	1961	$550,969,964

Now let’s examine the majority of our data for Cluster 2:

Code

# Cluster 2 Scatterplot
# y is our independent variable (NMTC Project Dollars),  
# x is our dependent variable (SVI flag count)

svi_divisional_county_nmtc_projects2 %>% 
  filter(cluster == 2) %>%
  ggplot2::ggplot(aes(x=flag_count10,
                    y=post10_nmtc_project_dollars)) +
        geom_point() +
        geom_smooth(method="lm") +
        scale_y_continuous(labels = scales::dollar_format())

Code

svi_divisional_county_nmtc_projects2 %>% 
  filter(cluster == 2) %>%
  select(flag_count10,post10_nmtc_project_dollars) %>%
  cor(method = "pearson")

                            flag_count10 post10_nmtc_project_dollars
flag_count10                     1.00000                     0.72778
post10_nmtc_project_dollars      0.72778                     1.00000

Here we can find that our correlation actually strengthened, indicating that the majority of our data points are in line with the trends of the overall data.

In addition, it seems the amount of money given to counties in the Middle Atlantic Division with 0 - 1,000 SVI flags is correlated with NMTC dollars from $0 to just over $90 million.

We can view these counties here:

Code

svi_divisional_county_nmtc_projects2 %>% 
  filter(cluster == 2) %>%
  select(county_name, flag_count10, post10_nmtc_dollars_formatted) %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

county_name	flag_count10	post10_nmtc_dollars_formatted
Bergen County, NJ	146	$10,000,000
Camden County, NJ	332	$79,664,200
Cumberland County, NJ	138	$33,187,593
Essex County, NJ	1019	$81,662,084
Hudson County, NJ	841	$110,136,049
Mercer County, NJ	225	$8,000,000
Middlesex County, NJ	226	$48,700,000
Ocean County, NJ	163	$1,900,000
Passaic County, NJ	447	$49,154,956
Union County, NJ	344	$20,700,000
Albany County, NY	85	$9,625,000
Allegany County, NY	29	$9,300,000
Broome County, NY	131	$5,280,000
Cattaraugus County, NY	44	$6,790,000
Cayuga County, NY	27	$6,240,000
Chautauqua County, NY	76	$39,360,000
Chenango County, NY	19	$58,819,000
Columbia County, NY	14	$9,700,000
Cortland County, NY	12	$2,000,000
Erie County, NY	528	$76,710,000
Monroe County, NY	574	$19,998,000
Nassau County, NY	151	$1,460,000
Onondaga County, NY	352	$20,428,080
Rensselaer County, NY	78	$7,020,000
Schenectady County, NY	68	$11,595,000
St. Lawrence County, NY	75	$1,920,000
Steuben County, NY	58	$7,680,000
Tompkins County, NY	32	$2,643,020
Westchester County, NY	424	$39,580,000
Adams County, PA	5	$14,161,000
Berks County, PA	219	$7,840,000
Clearfield County, PA	44	$26,360,000
Dauphin County, PA	140	$32,123,500
Delaware County, PA	236	$14,190,000
Erie County, PA	184	$7,358,392
Jefferson County, PA	25	$11,453,160
Lackawanna County, PA	107	$19,075,000
Lancaster County, PA	114	$12,514,500
Lebanon County, PA	38	$5,335,000
Lycoming County, PA	55	$25,440,000
Mercer County, PA	54	$18,440,000
Mifflin County, PA	37	$12,130,000
Northampton County, PA	86	$18,260,000
Washington County, PA	76	$12,760,000
Westmoreland County, PA	108	$6,737,500
York County, PA	143	$20,127,500

Thus, we can conclude here that for the majority of the counties in the Middle Atlantic Division, there’s a fairly strong positive correlation between more vulnerable counties receiving more NMTC money than less vulnerable counties.

Bivariate Map

Now let’s plot this relationship spatially:

To begin, we can load our divisional mapping data from Lab 03:

Code

divisional_county_sf <- svi_county_map2010 %>% select(COUNTYFP, STATEFP, geometry)

divisional_county_sf %>% head(5)

Simple feature collection with 5 features and 2 fields
Geometry type: MULTIPOLYGON
Dimension:     XY
Bounding box:  xmin: -75.14001 ymin: 38.92852 xmax: -73.89398 ymax: 41.13419
Geodetic CRS:  NAD83
  COUNTYFP STATEFP                       geometry
1      001      34 MULTIPOLYGON (((-74.42314 3...
2      003      34 MULTIPOLYGON (((-73.92676 4...
3      005      34 MULTIPOLYGON (((-74.99056 4...
4      007      34 MULTIPOLYGON (((-75.14001 3...
5      009      34 MULTIPOLYGON (((-74.94545 3...

Code

# Join our NMTC projects data with our shapefile geocoordinates
svi_divisional_county_nmtc_sf <- left_join(svi_divisional_county_nmtc_projects, divisional_county_sf, join_by("FIPS_st" == "STATEFP", "FIPS_county" == "COUNTYFP"))

svi_divisional_county_nmtc_sf %>% head(5) %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

State	County	Division	post10_nmtc_project_cnt	tract_cnt	post10_nmtc_project_dollars	post10_nmtc_dollars_formatted	fips_county_st	FIPS_st	FIPS_county	state_name	region_number	region	division_number	flag_count10	pop10	flag_by_pop10	flag_count_quantile10	flag_pop_quantile10	flag_count20	pop20	flag_by_pop20	flag_count_quantile20	flag_pop_quantile20	county_name	geometry
NJ	Bergen County	Middle Atlantic Division	1	30	10000000	$10,000,000	34003	34	003	New Jersey	1	Northeast Region	2	146	143973	0.0010141	1.0	0.4	165	154365	0.0010689	1.0	0.4	Bergen County, NJ	MULTIPOLYGON (((-73.92676 4...
NJ	Camden County	Middle Atlantic Division	5	47	79664200	$79,664,200	34007	34	007	New Jersey	1	Northeast Region	2	332	183630	0.0018080	1.0	1.0	315	180659	0.0017436	1.0	0.8	Camden County, NJ	MULTIPOLYGON (((-75.14001 3...
NJ	Cumberland County	Middle Atlantic Division	2	21	33187593	$33,187,593	34011	34	011	New Jersey	1	Northeast Region	2	138	101151	0.0013643	0.8	0.6	135	97989	0.0013777	0.8	0.6	Cumberland County, NJ	MULTIPOLYGON (((-75.1145 39...
NJ	Essex County	Middle Atlantic Division	6	115	81662084	$81,662,084	34013	34	013	New Jersey	1	Northeast Region	2	1019	385872	0.0026408	1.0	1.0	1039	385359	0.0026962	1.0	1.0	Essex County, NJ	MULTIPOLYGON (((-74.13892 4...
NJ	Hudson County	Middle Atlantic Division	5	100	110136049	$110,136,049	34017	34	017	New Jersey	1	Northeast Region	2	841	385737	0.0021802	1.0	1.0	802	404100	0.0019847	1.0	1.0	Hudson County, NJ	MULTIPOLYGON (((-74.02039 4...

Code

# Create classes for bivariate mapping 
svi_divisional_county_nmtc_sf <- bi_class(svi_divisional_county_nmtc_sf, x = flag_count10, y = post10_nmtc_project_dollars, style = "quantile", dim = 3)

# View data
svi_divisional_county_nmtc_sf %>% head(5) %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

State	County	Division	post10_nmtc_project_cnt	tract_cnt	post10_nmtc_project_dollars	post10_nmtc_dollars_formatted	fips_county_st	FIPS_st	FIPS_county	state_name	region_number	region	division_number	flag_count10	pop10	flag_by_pop10	flag_count_quantile10	flag_pop_quantile10	flag_count20	pop20	flag_by_pop20	flag_count_quantile20	flag_pop_quantile20	county_name	geometry	bi_class
NJ	Bergen County	Middle Atlantic Division	1	30	10000000	$10,000,000	34003	34	003	New Jersey	1	Northeast Region	2	146	143973	0.0010141	1.0	0.4	165	154365	0.0010689	1.0	0.4	Bergen County, NJ	MULTIPOLYGON (((-73.92676 4...	2-2
NJ	Camden County	Middle Atlantic Division	5	47	79664200	$79,664,200	34007	34	007	New Jersey	1	Northeast Region	2	332	183630	0.0018080	1.0	1.0	315	180659	0.0017436	1.0	0.8	Camden County, NJ	MULTIPOLYGON (((-75.14001 3...	3-3
NJ	Cumberland County	Middle Atlantic Division	2	21	33187593	$33,187,593	34011	34	011	New Jersey	1	Northeast Region	2	138	101151	0.0013643	0.8	0.6	135	97989	0.0013777	0.8	0.6	Cumberland County, NJ	MULTIPOLYGON (((-75.1145 39...	2-3
NJ	Essex County	Middle Atlantic Division	6	115	81662084	$81,662,084	34013	34	013	New Jersey	1	Northeast Region	2	1019	385872	0.0026408	1.0	1.0	1039	385359	0.0026962	1.0	1.0	Essex County, NJ	MULTIPOLYGON (((-74.13892 4...	3-3
NJ	Hudson County	Middle Atlantic Division	5	100	110136049	$110,136,049	34017	34	017	New Jersey	1	Northeast Region	2	841	385737	0.0021802	1.0	1.0	802	404100	0.0019847	1.0	1.0	Hudson County, NJ	MULTIPOLYGON (((-74.02039 4...	3-3

Finally we can create our map:

Code

# Create map with ggplot
svi_divisional_county_nmtc_map <- ggplot() +
  # Map county shapefile, fill with bi_class categories
  geom_sf(data = svi_divisional_county_nmtc_sf, mapping = aes(geometry=geometry, fill = bi_class), color = "white", size = 0.1, show.legend = FALSE) +
  # Set to biscale palette
  bi_scale_fill(pal = "GrPink", dim = 3) +
  # Add state shapefiles for outline
  geom_sf(data=divisional_st_sf, color="black", fill=NA, linewidth=.5, aes(geometry=geometry)) +
  labs(
    title = paste0("Correlation of 2010 ", census_division, " SVI Flag Count \n and 2011 - 2020 NMTC Tax Dollars"),
  ) +
  # Set them to biscale
  bi_theme(base_size = 10)

# Create biscale legend
svi_divisional_county_nmtc_legend <- bi_legend(pal = "GrPink",
                    dim = 3,
                    xlab = "SVI Flag Count",
                    ylab = "NMTC Dollars",
                    size = 8)

# Combine map with legend using cowplot
svi_divisional_county_nmtc_bivarmap <- ggdraw() +
  draw_plot(svi_divisional_county_nmtc_map) +
  # Set legend location
  draw_plot(svi_divisional_county_nmtc_legend, x= -.02,  y = -.05,
 width=.20)


# View map
svi_divisional_county_nmtc_bivarmap

Here we can see the distribution of our counties with NMTC projects based on the correlation between 2010 SVI Flag Count and NMTC dollars for the Middle Atlantic Division.

Here we can see that our high NMTC dollars and high SVI flag counts are largely clustered in the NYC metro area across NY and NJ:

Code

svi_divisional_county_nmtc_sf %>% filter(State %in% c("NY", "NJ")) %>% select(State, County, flag_count10, post10_nmtc_dollars_formatted) %>% arrange(desc(flag_count10)) %>% head(6) %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

State	County	flag_count10	post10_nmtc_dollars_formatted
NY	Kings County	3869	$216,348,600
NY	Bronx County	2688	$306,355,715
NY	Queens County	2347	$85,225,100
NJ	Essex County	1019	$81,662,084
NY	New York County	879	$255,545,686
NJ	Hudson County	841	$110,136,049

In contrast, on a divisional level PA has several counties with low SVI flag counts, but moderate-to-high NMTC dollars

Code

svi_divisional_county_nmtc_sf %>% filter(State == "PA") %>%
  arrange(desc(post10_nmtc_project_dollars), flag_count10) %>% select(State, County, flag_count10, post10_nmtc_dollars_formatted) %>% head(10) %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

State	County	flag_count10	post10_nmtc_dollars_formatted
PA	Philadelphia County	1961	$550,969,964
PA	Allegheny County	712	$244,342,400
PA	Dauphin County	140	$32,123,500
PA	Clearfield County	44	$26,360,000
PA	Lycoming County	55	$25,440,000
PA	York County	143	$20,127,500
PA	Lackawanna County	107	$19,075,000
PA	Mercer County	54	$18,440,000
PA	Northampton County	86	$18,260,000
PA	Delaware County	236	$14,190,000

LIHTC

Correlation between outcome & intervention

We can now repeat our divisional analysis for the LIHTC to identify if there is a relationship between dollars counties received from this program and the SVI flags.

Recall that we will want to review our summary statistics, a scatterplot, and a calculation of Pearson’s r to measure the correlation.

First let’s create a dataset of only counties with LIHTC projects:

Code

svi_divisional_county_lihtc_projects <- svi_divisional_county_lihtc %>% filter(post10_lihtc_project_cnt > 0)

Check division:

Code

svi_divisional_county_lihtc_projects %>% select(Division) %>% unique()

                  Division
1 Middle Atlantic Division

Now let’s review the summary statistics for our data set:

Code

summary(svi_divisional_county_lihtc_projects$flag_count10)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
   1.00   22.75   66.50  140.82  169.50 1154.00

Code

summary(svi_divisional_county_lihtc_projects$post10_lihtc_project_dollars)

    Min.  1st Qu.   Median     Mean  3rd Qu.     Max. 
       0  1197587  2015493  4533949  4904236 26054976

Note once again that unlike the NMTC program, there are instances where there are tracts with LIHTC projects, but they did not receive any funding. We want to filter these out of our data set for the purposes of our analysis of the relationship between LIHTC dollars and the SVI flags.

Code

svi_divisional_county_lihtc_projects <- svi_divisional_county_lihtc_projects %>% filter(post10_lihtc_project_dollars > 0)

Now we can view the updated summaries:

Code

summary(svi_divisional_county_lihtc_projects$flag_count10)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
    1.0    20.0    66.0   142.9   170.0  1154.0

Code

summary(svi_divisional_county_lihtc_projects$post10_lihtc_project_dollars)

    Min.  1st Qu.   Median     Mean  3rd Qu.     Max. 
   78558  1317572  2220667  4671341  4944903 26054976

The minimum flag count for the LIHTC program in the Middle Atlantic Division is 1 and the maximum is only 1,154 compared to 5 - 3,869 for NMTC. The LIHTC dollar amount range is $78,558 to over $26 million.

Once again, let’s view this visually in a scatterplot:

Code

# Scatterplot
# y is our independent variable (LIHTC Project Dollars),  
# x is our dependent variable (SVI flag count)
ggplot2::ggplot(svi_divisional_county_lihtc_projects,
                aes(x=flag_count10,
                    y=post10_lihtc_project_dollars)) +
        geom_point() +
        geom_smooth(method="lm") +
        scale_y_continuous(labels = scales::dollar_format())

Code

# Pearson's r calculation
cor(svi_divisional_county_lihtc_projects$flag_count10, svi_divisional_county_lihtc_projects$post10_lihtc_project_dollars, method = "pearson")

[1] 0.8106627

When we consider ALL counties in the Middle Atlantic Division, we have a very strong positive correlation between SVI Flag Counts in 2010 and and LIHTC dollars from 2011-2020, suggesting that counties that had more social vulnerability in 2010 received more LIHTC dollars in 2011-2020.

However, from visual inspection it appears we have an influential point in our data as well as some scatter.

Let’s explore this in a box plot:

Code

boxplot(svi_divisional_county_lihtc_projects$flag_count10)

Code

boxplot.stats(svi_divisional_county_lihtc_projects$flag_count10)$out %>% sort(decreasing = TRUE)

[1] 1154  570  471

This is our same influential point from our NMTC analysis, Kings County, NY:

Code

svi_divisional_county_lihtc_projects %>% filter(flag_count10 == 1154) %>% select(county_name, flag_count10, post10_lihtc_dollars_formatted) %>% head()

       county_name flag_count10 post10_lihtc_dollars_formatted
1 Kings County, NY         1154                    $26,054,976

K-Means Clustering

Now let’s conduct a cluster analysis:

Code

svi_divisional_lihtc_cluster <- svi_divisional_county_lihtc_projects %>% 
                            select(county_name, post10_lihtc_project_dollars, 
                                   flag_count10) %>% 
                            remove_rownames %>% 
                            column_to_rownames(var="county_name")

# Remove nulls, if in dataset
svi_divisional_lihtc_cluster <- na.omit(svi_divisional_lihtc_cluster)


# Scale numeric variables
svi_divisional_lihtc_cluster <- scale(svi_divisional_lihtc_cluster)


svi_divisional_lihtc_cluster %>% head(5)

                     post10_lihtc_project_dollars flag_count10
Atlantic County, NJ                   -0.52731441   -0.4795562
Essex County, NJ                       0.45524835    1.8980244
Mercer County, NJ                     -0.76318273   -0.3151254
Middlesex County, NJ                  -0.48543941   -0.1240301
Passaic County, NJ                    -0.01772409    0.2714926

Next we can try a few different cluster numbers and allow the algorithm to search through 25 sets to identify the best groupings for each number:

Code

set.seed(123)
k2_lihtc_div <- kmeans(svi_divisional_lihtc_cluster, centers = 2, nstart = 25)
set.seed(123)
k3_lihtc_div <- kmeans(svi_divisional_lihtc_cluster, centers = 3, nstart = 25)
set.seed(123)
k4_lihtc_div <- kmeans(svi_divisional_lihtc_cluster, centers = 4, nstart = 25)
set.seed(123)
k5_lihtc_div <- kmeans(svi_divisional_lihtc_cluster, centers = 5, nstart = 25)

Next we can view the plots to visually check the groupings and see if there’s any overlap:

Code

# plots to compare
p_k2_lihtc_div <- factoextra::fviz_cluster(k2_lihtc_div, geom = "point", data = svi_divisional_lihtc_cluster) + ggtitle("k = 2")

p_k3_lihtc_div <- factoextra::fviz_cluster(k3_lihtc_div, geom = "point", data = svi_divisional_lihtc_cluster) + ggtitle("k = 3")

p_k4_lihtc_div <- factoextra::fviz_cluster(k4_lihtc_div, geom = "point",  data = svi_divisional_lihtc_cluster) + ggtitle("k = 4")

p_k5_lihtc_div <- factoextra::fviz_cluster(k5_lihtc_div, geom = "point",  data = svi_divisional_lihtc_cluster) + ggtitle("k = 5")

grid.arrange(p_k2_lihtc_div, p_k3_lihtc_div, p_k4_lihtc_div, p_k5_lihtc_div, nrow = 2)

Similar to NMTC, it appears it may be best to divide our data into 2 clusters, but let’s check our Elbow Plot:

Code

elbow_plot(svi_divisional_lihtc_cluster)

[1] 1
[1] 2
[1] 3
[1] 4
[1] 5
[1] 6
[1] 7
[1] 8
[1] 9
[1] 10
[1] 11
[1] 12
[1] 13
[1] 14
[1] 15

Here we can see that the spacing between clusters actually decreases substantially after 3. Thus, we will go with 3 clusters for LIHTC for the Middle Atlantic Division:

Code

p_k3_lihtc_div <- factoextra::fviz_cluster(k3_lihtc_div, geom = "point", data = svi_divisional_lihtc_cluster) + ggtitle("k = 3")

p_k3_lihtc_div

We can then transform our cluster matrix back to a data frame and assign these clusters to our counties:

Code

svi_divisional_lihtc_cluster_label <- as.data.frame(svi_divisional_lihtc_cluster) %>%
                                  rownames_to_column(var = "county_name") %>%
                                  as_tibble() %>%
                                  mutate(cluster = k3_lihtc_div$cluster) %>%
                                  select(county_name, cluster)

svi_divisional_county_lihtc_projects2 <- left_join(svi_divisional_county_lihtc_projects, svi_divisional_lihtc_cluster_label, join_by(county_name == county_name))

# View county counts in each cluster
table(svi_divisional_county_lihtc_projects2$cluster)


 1  2  3 
26  6  1

Now we can re-examine the correlation between 2010 SVI Flag Counts and LIHTC Project Dollars for each subset of our data.

First recall our overall outcomes:

Code

# Overall Scatterplot
# y is our independent variable (LIHTC Project Dollars),  
# x is our dependent variable (SVI flag count)
ggplot2::ggplot(svi_divisional_county_lihtc_projects2,
                aes(x=flag_count10,
                    y=post10_lihtc_project_dollars)) +
        geom_point() +
        geom_smooth(method="lm") +
        scale_y_continuous(labels = scales::dollar_format())

Code

# Pearson's r calculation
cor(svi_divisional_county_lihtc_projects2$flag_count10, svi_divisional_county_lihtc_projects2$post10_lihtc_project_dollars, method = "pearson")

[1] 0.8106627

First let’s look at our cluster 1 data (bottom left cluster):

Code

# Cluster 1 Scatterplot
# y is our independent variable (LIHTC Project Dollars),  
# x is our dependent variable (SVI flag count)

svi_divisional_county_lihtc_projects2 %>% 
  filter(cluster == 1) %>%
  ggplot2::ggplot(aes(x=flag_count10,
                    y=post10_lihtc_project_dollars)) +
        geom_point() +
        geom_smooth(method="lm") +
        scale_y_continuous(labels = scales::dollar_format())

Code

svi_divisional_county_lihtc_projects2 %>% 
  filter(cluster == 1) %>%
  select(flag_count10,post10_lihtc_project_dollars) %>%
  cor(method = "pearson")

                             flag_count10 post10_lihtc_project_dollars
flag_count10                    1.0000000                    0.5231078
post10_lihtc_project_dollars    0.5231078                    1.0000000

Here we can find that we still have a positive correlation, though it has weakened to a moderate correlation from very strong. Thus, we can conlude that Kings County, NY is indeed an influential point that pulls our regression line and correlation to be stronger than the trend of the majority of our data.

Now let’s examine our middle points in Cluster 2:

Code

# Cluster 2 Scatterplot
# y is our independent variable (LIHTC Project Dollars),  
# x is our dependent variable (SVI flag count)

svi_divisional_county_lihtc_projects2 %>% 
  filter(cluster == 2) %>%
  ggplot2::ggplot(aes(x=flag_count10,
                    y=post10_lihtc_project_dollars)) +
        geom_point() +
        geom_smooth(method="lm") +
        scale_y_continuous(labels = scales::dollar_format())

Code

svi_divisional_county_lihtc_projects2 %>% 
  filter(cluster == 2) %>%
  select(flag_count10,post10_lihtc_project_dollars) %>%
  cor(method = "pearson")

                             flag_count10 post10_lihtc_project_dollars
flag_count10                  1.000000000                 -0.008926241
post10_lihtc_project_dollars -0.008926241                  1.000000000

Here we can see that our data is too scattered to identify a correlation.

Finally, let’s look at our upper end county data in cluster 3:

Code

# Cluster 3 Scatterplot
# y is our independent variable (LIHTC Project Dollars),  
# x is our dependent variable (SVI flag count)

svi_divisional_county_lihtc_projects2 %>% 
  filter(cluster == 3) %>%
  ggplot2::ggplot(aes(x=flag_count10,
                    y=post10_lihtc_project_dollars)) +
        geom_point() +
        geom_smooth(method="lm") +
        scale_y_continuous(labels = scales::dollar_format())

Code

svi_divisional_county_lihtc_projects2 %>% 
  filter(cluster == 3) %>%
  select(flag_count10,post10_lihtc_project_dollars) %>%
  cor(method = "pearson")

                             flag_count10 post10_lihtc_project_dollars
flag_count10                           NA                           NA
post10_lihtc_project_dollars           NA                           NA

With only one point, Kings County, NY, we cannot calculate a correlation.

Code

svi_divisional_county_lihtc_projects2 %>% 
  filter(cluster == 3) %>%
  select(county_name, flag_count10, post10_lihtc_dollars_formatted) %>% 
  arrange(desc(flag_count10)) %>% head(10) %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

county_name	flag_count10	post10_lihtc_dollars_formatted
Kings County, NY	1154	$26,054,976

Thus, we can conclude that the majority of our data follows the trend of a positive correlation between 2010 SVI Flag Counts and LIHTC dollars in our division. However, this relationship weakens for counties with mid-range vulnerability and dollars received.

Bivariate Map

Now let’s view this relationship spatially by creating a bivariate map.

Code

# Join our LIHTC projects data with our shapefile geocoordinates
svi_divisional_county_lihtc_sf <- left_join(svi_divisional_county_lihtc_projects, divisional_county_sf, join_by("FIPS_st" == "STATEFP", "FIPS_county" == "COUNTYFP"))

svi_divisional_county_lihtc_sf %>% head(5) %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

State	County	Division	post10_lihtc_project_cnt	tract_cnt	post10_lihtc_project_dollars	post10_lihtc_dollars_formatted	fips_county_st	FIPS_st	FIPS_county	state_name	region_number	region	division_number	flag_count10	pop10	flag_by_pop10	flag_count_quantile10	flag_pop_quantile10	flag_count20	pop20	flag_by_pop20	flag_count_quantile20	flag_pop_quantile20	county_name	geometry
NJ	Atlantic County	Middle Atlantic Division	1	3	1497998	$1,497,998	34001	34	001	New Jersey	1	Northeast Region	2	35	7939	0.0044086	0.8	1.0	37	8027	0.0046094	0.8	1.0	Atlantic County, NJ	MULTIPOLYGON (((-74.42314 3...
NJ	Essex County	Middle Atlantic Division	6	60	7410996	$7,410,996	34013	34	013	New Jersey	1	Northeast Region	2	570	190447	0.0029930	1.0	0.8	577	189347	0.0030473	1.0	0.8	Essex County, NJ	MULTIPOLYGON (((-74.13892 4...
NJ	Mercer County	Middle Atlantic Division	3	8	78558	$78,558	34021	34	021	New Jersey	1	Northeast Region	2	72	23722	0.0030352	1.0	0.8	79	22886	0.0034519	1.0	1.0	Mercer County, NJ	MULTIPOLYGON (((-74.77831 4...
NJ	Middlesex County	Middle Atlantic Division	1	13	1749999	$1,749,999	34023	34	023	New Jersey	1	Northeast Region	2	115	61228	0.0018782	1.0	0.4	114	64219	0.0017752	1.0	0.4	Middlesex County, NJ	MULTIPOLYGON (((-74.20896 4...
NJ	Passaic County	Middle Atlantic Division	5	20	4564679	$4,564,679	34031	34	031	New Jersey	1	Northeast Region	2	204	86099	0.0023694	1.0	0.6	200	88872	0.0022504	1.0	0.6	Passaic County, NJ	MULTIPOLYGON (((-74.38946 4...

Code

# Create classes for bivariate mapping 
svi_divisional_county_lihtc_sf <- bi_class(svi_divisional_county_lihtc_sf, x = flag_count10, y = post10_lihtc_project_dollars, style = "quantile", dim = 3)

# View data
svi_divisional_county_lihtc_sf %>% head(5) %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

State	County	Division	post10_lihtc_project_cnt	tract_cnt	post10_lihtc_project_dollars	post10_lihtc_dollars_formatted	fips_county_st	FIPS_st	FIPS_county	state_name	region_number	region	division_number	flag_count10	pop10	flag_by_pop10	flag_count_quantile10	flag_pop_quantile10	flag_count20	pop20	flag_by_pop20	flag_count_quantile20	flag_pop_quantile20	county_name	geometry	bi_class
NJ	Atlantic County	Middle Atlantic Division	1	3	1497998	$1,497,998	34001	34	001	New Jersey	1	Northeast Region	2	35	7939	0.0044086	0.8	1.0	37	8027	0.0046094	0.8	1.0	Atlantic County, NJ	MULTIPOLYGON (((-74.42314 3...	1-1
NJ	Essex County	Middle Atlantic Division	6	60	7410996	$7,410,996	34013	34	013	New Jersey	1	Northeast Region	2	570	190447	0.0029930	1.0	0.8	577	189347	0.0030473	1.0	0.8	Essex County, NJ	MULTIPOLYGON (((-74.13892 4...	3-3
NJ	Mercer County	Middle Atlantic Division	3	8	78558	$78,558	34021	34	021	New Jersey	1	Northeast Region	2	72	23722	0.0030352	1.0	0.8	79	22886	0.0034519	1.0	1.0	Mercer County, NJ	MULTIPOLYGON (((-74.77831 4...	2-1
NJ	Middlesex County	Middle Atlantic Division	1	13	1749999	$1,749,999	34023	34	023	New Jersey	1	Northeast Region	2	115	61228	0.0018782	1.0	0.4	114	64219	0.0017752	1.0	0.4	Middlesex County, NJ	MULTIPOLYGON (((-74.20896 4...	2-2
NJ	Passaic County	Middle Atlantic Division	5	20	4564679	$4,564,679	34031	34	031	New Jersey	1	Northeast Region	2	204	86099	0.0023694	1.0	0.6	200	88872	0.0022504	1.0	0.6	Passaic County, NJ	MULTIPOLYGON (((-74.38946 4...	3-3

Finally we can create our map:

Code

# Create map with ggplot
svi_divisional_county_lihtc_map <- ggplot() +
  # Map county shapefile, fill with bi_class categories
  geom_sf(data = svi_divisional_county_lihtc_sf, mapping = aes(geometry=geometry, fill = bi_class), color = "white", size = 0.1, show.legend = FALSE) +
  # Set to biscale palette
  bi_scale_fill(pal = "GrPink", dim = 3) +
  # Add state shapefiles for outline
  geom_sf(data=divisional_st_sf, color="black", fill=NA, linewidth=.5, aes(geometry=geometry)) +
  labs(
    title = paste0("Correlation of 2010 ", census_division, " SVI Flag Count \n and 2011 - 2020 LIHTC Tax Dollars")
  ) +
  # Set them to biscale
  bi_theme(base_size = 10)

# Create biscale legend
svi_divisional_county_lihtc_legend <- bi_legend(pal = "GrPink",
                    dim = 3,
                    xlab = "SVI Flag Count",
                    ylab = "LIHTC Dollars",
                    size = 8)

# Combine map with legend using cowplot
svi_divisional_county_lihtc_bivarmap <- ggdraw() +
  draw_plot(svi_divisional_county_lihtc_map) +
  # Set legend location
  draw_plot(svi_divisional_county_lihtc_legend, x= -.02,  y = -.05,
 width=.20)


# View map
svi_divisional_county_lihtc_bivarmap

Here we can see the distribution of our LIHTC counties is quite a bit less than our NMTC projects as we would expect based on national trends.

Several of our counties in NY have either both moderate SVI flag count and moderate LIHTC dollars count or high SVI flag count and high LIHTC dollars.

The NYC, Pittsburgh, and Philadelphia metros have high SVI flag and high LIHTC dollars:

Code

svi_divisional_county_lihtc_sf %>% filter(State == "NY") %>% select(State, County, flag_count10, post10_lihtc_dollars_formatted) %>% arrange(desc(flag_count10)) %>% head(6)

  State          County flag_count10 post10_lihtc_dollars_formatted
1    NY    Kings County         1154                    $26,054,976
2    NY    Bronx County          471                    $19,909,800
3    NY   Queens County          310                     $4,094,899
4    NY New York County          206                     $9,337,368
5    NY   Monroe County          170                     $4,944,903
6    NY     Erie County          168                     $2,220,667

Code

svi_divisional_county_lihtc_sf %>% filter(State == "NJ") %>% select(State, County, flag_count10, post10_lihtc_dollars_formatted) %>% arrange(desc(flag_count10)) %>% head(6)

  State           County flag_count10 post10_lihtc_dollars_formatted
1    NJ     Essex County          570                     $7,410,996
2    NJ   Passaic County          204                     $4,564,679
3    NJ Middlesex County          115                     $1,749,999
4    NJ    Mercer County           72                        $78,558
5    NJ     Union County           66                     $6,296,201
6    NJ  Atlantic County           35                     $1,497,998

Code

svi_divisional_county_lihtc_sf %>% filter(State == "PA") %>% select(State, County, flag_count10, post10_lihtc_dollars_formatted) %>% arrange(desc(flag_count10)) %>% head(6)

  State              County flag_count10 post10_lihtc_dollars_formatted
1    PA Philadelphia County          261                     $6,805,843
2    PA    Allegheny County          185                     $8,889,633
3    PA         Erie County           70                       $944,622
4    PA        Berks County           50                       $705,044
5    PA     Delaware County           31                     $3,437,127
6    PA        Blair County           10                       $736,262

Save data sets

Code

saveRDS(svi_divisional_lihtc, file = here::here(paste0("data/wrangling/", str_replace_all(census_division, " ", "_"), "_svi_divisional_lihtc.rds")))

saveRDS(svi_national_lihtc, file = here::here(paste0("data/wrangling/", str_replace_all(census_division, " ", "_"), "_svi_national_lihtc.rds")))

saveRDS(svi_divisional_nmtc, file = here::here(paste0("data/wrangling/", str_replace_all(census_division, " ", "_"), "_svi_divisional_nmtc.rds")))

saveRDS(svi_national_nmtc, file = here::here(paste0("data/wrangling/", str_replace_all(census_division, " ", "_"), "_svi_national_nmtc.rds")))

Lab Submission Instructions

Congratulations! You’ve reached the end of the Lab-04 Tutorial!

You are now ready to complete your lab and submit it on Canvas.

Note

Your import step in your .RMD file should look similar to the code chunk below, but your project_data_steps.R file should have your initials on the end (i.e. project_data_steps_CS.R).

Code

import::here( "fips_census_regions",
              "load_svi_data",
              "merge_svi_data",
              "census_division",
              "flag_summarize",
              "summarize_county_nmtc",
              "summarize_county_lihtc",
              "elbow_plot",
             # notice the use of here::here() that points to the .R file
             # where all these R objects are created
             .from = here::here("analysis/project_data_steps.R"),
             .character_only = TRUE)

The following checklist will ensure that you’re on track:

Add newly created graphing and data wrangling functions to project_data_steps.R file
Create new .RMD file and load data and functions from project_data_steps.R file
Create 2 NMTC data sets on a national and census-division level
Calculate overall correlation between SVI Flag Count in 2010 and NMTC Dollars received from 2011-2020 by county for your Census Division, describe findings
Conduct k-means clustering and calculate the correlation between SVI Flag Count in 2010 and NMTC Dollars received from 2011-2020 by clustered county group for your Census Division, describe findings
Create bivariate map of SVI Flag Count in 2010 and NMTC Dollars received for your Census Division
Create 2 LIHTC data sets on a national and census-division level
Calculate overall correlation between SVI Flag Count in 2010 and LIHTC Dollars received from 2011-2020 by county for your Census Division, describe findings
Conduct k-means clustering and calculate the correlation between SVI Flag Count in 2010 and LIHTC Dollars received from 2011-2020 by clustered county group for your Census Division, describe findings <br Create bivariate map of SVI Flag Count in 2010 and LIHTC Dollars received for your Census Division
Apply code chunk options to hide any unwanted warnings/messages
Knit .RMD file to create .HTML and .md (Github Flavored) for output
Review example report to get a general idea of what your output should look like
Submit project_data_steps.R, .RMD, .HTML, and .MD files to Canvas
Treat yourself for a job well-done!