Homework 3

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.2.0     ✔ readr     2.1.6
## ✔ forcats   1.0.1     ✔ stringr   1.6.0
## ✔ ggplot2   4.0.1     ✔ tibble    3.3.1
## ✔ lubridate 1.9.5     ✔ tidyr     1.3.2
## ✔ purrr     1.2.1     
## ── 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)

district<-read_excel("district.xls")

new_data<-district %>% select(DISTNAME,DPETSPEP,DPFPASPEP)

summary(new_data)

##    DISTNAME            DPETSPEP       DPFPASPEP     
##  Length:1207        Min.   : 0.00   Min.   : 0.000  
##  Class :character   1st Qu.: 9.90   1st Qu.: 5.800  
##  Mode  :character   Median :12.10   Median : 8.900  
##                     Mean   :12.27   Mean   : 9.711  
##                     3rd Qu.:14.20   3rd Qu.:12.500  
##                     Max.   :51.70   Max.   :49.000  
##                                     NA's   :5

#DPFPASPEP has 5 missing variables
new_data_no_missing<-new_data %>% drop_na
#There are 1202 observations after dropping the NA responses

ggplot(new_data_no_missing,aes(x=DPETSPEP,y=DPFPASPEP)) + geom_point()

#The amount of money for special ed seems related to the percentage of special ed students.

cor(new_data_no_missing$DPETSPEP,new_data_no_missing$DPFPASPEP)

## [1] 0.3700234

#There is a weak positive correlation.