I will be using the 2022_ EAVS_for_Public_Release_V1.1.xlsx dataset, which contains sufficient observations and variables to conduct meaningful analysis relevant to my research topic. The dataset is free of personal or sensitive information and is authorized for public distribution and disclosure.

My paper will focus specifically on the state of Texas, but it is highly relevant to the study of Public Administration for several key reasons. One significant factor is the importance of understanding mail-in voting, as it directly impacts election integrity, voter participation, and administrative efficiency. Additionally, the public perception of mail-in voting has undergone a dramatic shift, mostly because of increased media scrutiny, security concerns, and allegations of irregularities, especially in the wake of the 2020 Presidential election. The outcome of the 2020 election led to the creation of new identification requirements, which in turn caused a notable rise in ballot rejections. Public administrators must carefully examine these disparities to ensure that all eligible voters are knowledgeable about how to correctly vote by mail in ballots and that their votes are accurately counted.

library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(readxl)
EAVS_for_Public_Release_V1.1.xlsx<-read_xlsx("2022_EAVS_for_Public_Release_V1.1.xlsx")
EAVS_for_Public_Release_V1.1.xlsx$A1a<-as.numeric(EAVS_for_Public_Release_V1.1.xlsx$A1a)
## Warning: NAs introduced by coercion
EAVS_for_Public_Release_V1.1.xlsx$A1b<-as.numeric(EAVS_for_Public_Release_V1.1.xlsx$A1b)
## Warning: NAs introduced by coercion
summary(EAVS_for_Public_Release_V1.1.xlsx$A1a)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##       0     840    4573   35349   18464 7412146      57
summary(EAVS_for_Public_Release_V1.1.xlsx$A1b)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##       0     814    4251   31827   16987 5618825      61
EAVS<-EAVS_for_Public_Release_V1.1.xlsx%>%select(A1a,A1b)%>%na.omit(.)
ggplot(EAVS,aes(x=A1a,y=A1b))+geom_point()

cor(EAVS$A1a,EAVS$A1b)
## [1] 0.9960543

The data is nearly 100% correlated.