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(tidyverse)
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
library(readxl)
district<-read_excel("district.xls")
district_data <-district
district_data<-lm(DA0GR21N~DPSTURNR+DPSTTOSA+DPSTADFP,data=district)
plot(district_data,which=1)
raintest(district_data)
##
## Rainbow test
##
## data: district_data
## Rain = 0.79774, df1 = 539, df2 = 535, p-value = 0.9955
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(district_data)
## lag Autocorrelation D-W Statistic p-value
## 1 0.1061114 1.78761 0.012
## Alternative hypothesis: rho != 0
plot(district_data,which=3)
bptest(district_data)
##
## studentized Breusch-Pagan test
##
## data: district_data
## BP = 37.448, df = 3, p-value = 3.7e-08
shapiro.test(district_data$residuals)
##
## Shapiro-Wilk normality test
##
## data: district_data$residuals
## W = 0.55805, p-value < 2.2e-16
district_data_1_robust<-rlm(DA0GR21N~DPSTADFP,data=district)
summary(district_data_1_robust)
##
## Call: rlm(formula = DA0GR21N ~ DPSTADFP, data = district)
## Residuals:
## Min 1Q Median 3Q Max
## -271.82 -71.75 -28.74 98.40 11464.69
##
## Coefficients:
## Value Std. Error t value
## (Intercept) 30.5710 10.3930 2.9415
## DPSTADFP 3.9803 0.4554 8.7397
##
## Residual standard error: 111.6 on 1077 degrees of freedom
## (128 observations deleted due to missingness)
summary(district_data_1_robust)
##
## Call: rlm(formula = DA0GR21N ~ DPSTADFP, data = district)
## Residuals:
## Min 1Q Median 3Q Max
## -271.82 -71.75 -28.74 98.40 11464.69
##
## Coefficients:
## Value Std. Error t value
## (Intercept) 30.5710 10.3930 2.9415
## DPSTADFP 3.9803 0.4554 8.7397
##
## Residual standard error: 111.6 on 1077 degrees of freedom
## (128 observations deleted due to missingness)
kitchen_sink<-lm(DA0GR21N~DPSTURNR+DPSTTOSA+DPSTADFP,data=district)
vif(kitchen_sink)
## DPSTURNR DPSTTOSA DPSTADFP
## 1.051593 1.188830 1.135042
plot(district_data,which=2)
district_clean<-district %>% drop_na()
district_data_log<-lm(log(DA0GR21N)~log(DPSTADFP),data=district_clean)
plot(district_data_log,which=2)
summary(district_data_log)
##
## Call:
## lm(formula = log(DA0GR21N) ~ log(DPSTADFP), data = district_clean)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.7864 -0.7354 -0.0380 0.7469 3.3715
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.07486 0.75668 0.099 0.921
## log(DPSTADFP) 1.87755 0.23819 7.883 5.04e-14 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.166 on 321 degrees of freedom
## Multiple R-squared: 0.1622, Adjusted R-squared: 0.1596
## F-statistic: 62.14 on 1 and 321 DF, p-value: 5.043e-14