library(readxl)
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 1.9.3     ✔ 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
district<-read_excel("district.xls")
newdata<-district %>% select(DISTNAME,DPETSPEP,DPFPASPEP)
summary(newdata$DISTNAME)
##    Length     Class      Mode 
##      1207 character character
summary(newdata$DPETSPEP)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    0.00    9.90   12.10   12.27   14.20   51.70
summary(newdata$DPFPASPEP)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   0.000   5.800   8.900   9.711  12.500  49.000       5

Variables with missing numbers in DPFPASPEP

newdataclean<-newdata %>% filter(!is.na(DPFPASPEP))

1202 left overall

ggplot(newdataclean,aes(DPFPASPEP,DPETSPEP))+geom_point()

Starts with small correlations and decreases in higher percent special education.

cor(newdataclean$DPFPASPEP,newdataclean$DPETSPEP)
## [1] 0.3700234