Homework 7

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 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.0.4     
## ── 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")

biligual<-district%>%select(DPETBILP,DPSTBIFP,DPSTTOSA,DPETHISP)

biligual_clean<-biligual%>%na.omit(.)

library(lmtest)

## Loading required package: zoo

## 
## Attaching package: 'zoo'

## The following objects are masked from 'package:base':
## 
##     as.Date, as.Date.numeric

library(MASS)

## 
## Attaching package: 'MASS'

## The following object is masked from 'package:dplyr':
## 
##     select

biligual_clean_model<-lm(DPETBILP~DPSTBIFP+DPSTTOSA+DPETHISP,data = biligual_clean)

plot(biligual_clean_model,which = 1)

raintest(biligual_clean_model)

## 
##  Rainbow test
## 
## data:  biligual_clean_model
## Rain = 0.7052, df1 = 602, df2 = 597, p-value = 1

library(car)

## Loading required package: carData

## 
## Attaching package: 'car'

## The following object is masked from 'package:dplyr':
## 
##     recode

## The following object is masked from 'package:purrr':
## 
##     some

durbinWatsonTest(biligual_clean_model)

##  lag Autocorrelation D-W Statistic p-value
##    1       0.2465686      1.504285       0
##  Alternative hypothesis: rho != 0

plot(biligual_clean_model,which = 3)

bptest(biligual_clean_model)

## 
##  studentized Breusch-Pagan test
## 
## data:  biligual_clean_model
## BP = 152.19, df = 3, p-value < 2.2e-16

plot(biligual_clean_model,which = 2)

shapiro.test(biligual_clean_model$residuals)

## 
##  Shapiro-Wilk normality test
## 
## data:  biligual_clean_model$residuals
## W = 0.85181, p-value < 2.2e-16

vif(biligual_clean_model)

## DPSTBIFP DPSTTOSA DPETHISP 
## 1.183359 1.062115 1.137910

biligual_clean_model<-district%>%dplyr::select(DPSTBIFP,DPSTTOSA,DPETHISP)

cor(biligual_clean_model)

##          DPSTBIFP DPSTTOSA DPETHISP
## DPSTBIFP        1       NA       NA
## DPSTTOSA       NA        1       NA
## DPETHISP       NA       NA        1