library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.2.1     ✔ readr     2.2.0
## ✔ forcats   1.0.1     ✔ stringr   1.6.0
## ✔ ggplot2   4.0.3     ✔ tibble    3.3.1
## ✔ lubridate 1.9.5     ✔ tidyr     1.3.2
## ✔ purrr     1.2.2     
## ── 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)

district <-read_excel("district (2).xls")
district_example<-district%>% select(DA0AT21R,DA0CSA21R) %>% arrange(-DA0AT21R,DA0CSA21R)

district_example
## # A tibble: 1,207 × 2
##    DA0AT21R DA0CSA21R
##       <dbl>     <dbl>
##  1    100        1241
##  2    100          NA
##  3     99.9        NA
##  4     99.7        NA
##  5     99.6      1048
##  6     99.6      1056
##  7     99.3        NA
##  8     99.3        NA
##  9     99.1        NA
## 10     99         997
## # ℹ 1,197 more rows
cor(district_example)
##           DA0AT21R DA0CSA21R
## DA0AT21R         1        NA
## DA0CSA21R       NA         1
cor(district_example, use = "pairwise.complete.obs")
##            DA0AT21R DA0CSA21R
## DA0AT21R  1.0000000 0.1247348
## DA0CSA21R 0.1247348 1.0000000

There is a weak correlation between the attendance rate and the SAT average score.

district_example1<-district%>% select(DPSTKIDR,DA0CSA21R) %>% arrange(-DPSTKIDR,DA0CSA21R)
district_example1
## # A tibble: 1,207 × 2
##    DPSTKIDR DA0CSA21R
##       <dbl>     <dbl>
##  1     37.3       971
##  2     26.9        NA
##  3     26.3        NA
##  4     24.9        -1
##  5     24.3        NA
##  6     23.2       923
##  7     23        1010
##  8     22.6        NA
##  9     22.4        NA
## 10     21.2        NA
## # ℹ 1,197 more rows
cor(district_example1, use = "pairwise.complete.obs")
##            DPSTKIDR DA0CSA21R
## DPSTKIDR  1.0000000 0.2659224
## DA0CSA21R 0.2659224 1.0000000

There is a weak correlation between the number of students per teacher and the SAT average score.

district_example2<-district%>% select(DPETECOP,DA0CSA21R) %>% arrange(-DPETECOP,DA0CSA21R)

district_example2
## # A tibble: 1,207 × 2
##    DPETECOP DA0CSA21R
##       <dbl>     <dbl>
##  1      100       894
##  2      100      1012
##  3      100        NA
##  4      100        NA
##  5      100        NA
##  6      100        NA
##  7      100        NA
##  8      100        NA
##  9      100        NA
## 10      100        NA
## # ℹ 1,197 more rows
cor(district_example2, use = "pairwise.complete.obs")
##             DPETECOP  DA0CSA21R
## DPETECOP   1.0000000 -0.2015739
## DA0CSA21R -0.2015739  1.0000000

There is a weak correlation between the STUDENTS: % ECONOMICALLY DISADVANTAGED and the SAT average score.

district_example3<-district%>% select(DPSTURNR,DA0CSA21R) %>% arrange(-DPSTURNR,DA0CSA21R)

district_example3
## # A tibble: 1,207 × 2
##    DPSTURNR DA0CSA21R
##       <dbl>     <dbl>
##  1    100          NA
##  2     81.2        NA
##  3     80        1006
##  4     79.5        NA
##  5     77.8        NA
##  6     69.8        NA
##  7     67.8       962
##  8     67         922
##  9     66.7        NA
## 10     66.5        NA
## # ℹ 1,197 more rows
cor(district_example3, use = "pairwise.complete.obs")
##              DPSTURNR   DA0CSA21R
## DPSTURNR   1.00000000 -0.07310558
## DA0CSA21R -0.07310558  1.00000000

There is no correlation between teacher turnover rate and the SAT average score.

pairs(~DA0AT21R+DPSTKIDR+DPETECOP+DPFVTOTK+DPFRAALLK,data=district)

cor.test(district_example$DA0AT21R,district_example$DA0CSA21R,method = "pearson")
## 
##  Pearson's product-moment correlation
## 
## data:  district_example$DA0AT21R and district_example$DA0CSA21R
## t = 3.8585, df = 942, p-value = 0.0001219
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.0614174 0.1870523
## sample estimates:
##       cor 
## 0.1247348
cor.test(district_example1$DPSTKIDR,district_example1$DA0CSA21R,method = "pearson")
## 
##  Pearson's product-moment correlation
## 
## data:  district_example1$DPSTKIDR and district_example1$DA0CSA21R
## t = 8.4575, df = 940, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.2055397 0.3242881
## sample estimates:
##       cor 
## 0.2659224

I tried 4 different variables I chose as my independent variables and I compared them to my dependent variable. All of them have a weak correlation to my dependent variable and i did the pearsons product moment correlation to the one with the most corenation which is .206 still weak but not as weak as the other ones. I also used this one because it has normal data. I did not use Kendall because it is for small sample sizes.