Homework 5

library(readxl)
district <- read_excel("district.xls")
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

obj2 <- district %>% select(DA0AT21R,DA0912DR21R)

obj2_cleaned <- obj2 %>% filter(!is.na(DA0AT21R)&(!is.na(DA0912DR21R))&(DA0912DR21R>0))

library(dplyr)

obj2_cleaned <- district %>% select(DA0AT21R,DA0912DR21R) %>% arrange

obj2_cleaned

## # A tibble: 1,207 × 2
##    DA0AT21R DA0912DR21R
##       <dbl>       <dbl>
##  1     96.7         0  
##  2     96           0.3
##  3     95.4         0.4
##  4     95.8         0  
##  5     93.7         0  
##  6     94.5         0  
##  7     96.7         0  
##  8     92.8         0.4
##  9     97.3         0.4
## 10     95.2         0.7
## # ℹ 1,197 more rows

cor(obj2_cleaned, use = "complete.obs")

##               DA0AT21R DA0912DR21R
## DA0AT21R     1.0000000  -0.3991648
## DA0912DR21R -0.3991648   1.0000000

pairs(obj2_cleaned[, c("DA0AT21R", "DA0912DR21R")])

``` r
cor.test(obj2_cleaned$DA0AT21R,obj2_cleaned$DA0912DR21R,method="pearson")

## 
##  Pearson's product-moment correlation
## 
## data:  obj2_cleaned$DA0AT21R and obj2_cleaned$DA0912DR21R
## t = -14.393, df = 1093, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.447817 -0.348156
## sample estimates:
##        cor 
## -0.3991648

#There is a moderately strong negative correlation between the two variables.The P-value is extrememly small which contains evidence against the null hypothesis.