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   3.5.2     ✔ tibble    3.3.0
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.1.0     
## ── 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)
library(pastecs)
## 
## Attaching package: 'pastecs'
## 
## The following objects are masked from 'package:dplyr':
## 
##     first, last
## 
## The following object is masked from 'package:tidyr':
## 
##     extract
setwd("C:/Users/KaeRo/Desktop/R Studio/Reseach Data Selection")
library(readxl)
district <- read_excel("district.xls")

CORRELATION TESTING————————————————————————————————————-

Teacher_percent<- district %>% select(DPSTBLFP,DPSTHIFP,DPSTWHFP,DPSTINFP,DPSTPIFP,DPSTTOSA) %>% drop_na()
cor(Teacher_percent)
##             DPSTBLFP    DPSTHIFP     DPSTWHFP     DPSTINFP     DPSTPIFP
## DPSTBLFP  1.00000000 -0.06114596 -0.499141527  0.054671612  0.088232503
## DPSTHIFP -0.06114596  1.00000000 -0.817625865 -0.091437442  0.010729376
## DPSTWHFP -0.49914153 -0.81762586  1.000000000  0.006730531 -0.074328408
## DPSTINFP  0.05467161 -0.09143744  0.006730531  1.000000000 -0.005833426
## DPSTPIFP  0.08823250  0.01072938 -0.074328408 -0.005833426  1.000000000
## DPSTTOSA  0.09898315  0.14264616 -0.193255525  0.020925351  0.086403715
##             DPSTTOSA
## DPSTBLFP  0.09898315
## DPSTHIFP  0.14264616
## DPSTWHFP -0.19325553
## DPSTINFP  0.02092535
## DPSTPIFP  0.08640372
## DPSTTOSA  1.00000000
pairs(~DPSTBLFP+DPSTHIFP+DPSTWHFP+DPSTINFP+DPSTPIFP+DPSTTOSA, data=Teacher_percent)

So average teacher pay doesn’t correlate with percentage of certain race But interestesting relationship with hispanic and white teachers (there is no other apparent correlation with other teacher races)

Cleaned_district<-district %>% drop_na()
cor(Cleaned_district$DPSTWHFP,Cleaned_district$DPETWHIP)
## [1] 0.8654033

So percentage of white teachers is somewhat correlated with percentage of white students

cor(Cleaned_district$DPETWHIP, Cleaned_district$DA0AT21R)
## [1] 0.210462

Percentage of white students not correlated with attendance rates

cor(Cleaned_district$DPETGIFP, Cleaned_district$DPETWHIP)
## [1] 0.01259812

Gifted and talented not correlated with percentage of white students

cor(Cleaned_district$DPETWHIP, Cleaned_district$DA0912DR21R)
## [1] -0.2865596

drop out rate is not correlated to percentage of white students

cor(Cleaned_district$DPSTTOSA, Cleaned_district$DPETBLAP)
## [1] 0.09129986

Teacher salary and percentage of african american children not correlated

VARIABLES OF INTEREST———————————————————————————————————— Comparing % of White Teachers & % of Hispanic Teachers

cor.test(Teacher_percent$DPSTWHFP,Teacher_percent$DPSTHIFP,method="kendall")
## 
##  Kendall's rank correlation tau
## 
## data:  Teacher_percent$DPSTWHFP and Teacher_percent$DPSTHIFP
## z = -36.587, p-value < 2.2e-16
## alternative hypothesis: true tau is not equal to 0
## sample estimates:
##        tau 
## -0.7098393

I used the Kendall’s rank in all honesty because I don’t think this data set will work with any of the others (not bell curve). The p- value is less than .05, so that means that there is some correlation? I think I’m reading that correctly.