library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.2.0     ✔ readr     2.1.6
## ✔ forcats   1.0.1     ✔ stringr   1.6.0
## ✔ ggplot2   4.0.2     ✔ tibble    3.3.1
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.2
## ✔ purrr     1.2.1     
## ── 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)
TEA_Data<-read_excel("district.xls")
Distric_model<-lm(DZRVLOCP~DPETALLC+COMMTYPE,data =TEA_Data)

summary(Distric_model)
## 
## Call:
## lm(formula = DZRVLOCP ~ DPETALLC + COMMTYPE, data = TEA_Data)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -49.798 -13.695  -3.468  11.452  54.019 
## 
## Coefficients:
##                                        Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                           4.724e+00  1.452e+00   3.254  0.00117 ** 
## DPETALLC                              1.332e-04  6.959e-05   1.914  0.05586 .  
## COMMTYPEIndependent Town              3.528e+01  3.091e+00  11.414  < 2e-16 ***
## COMMTYPEMajor Suburban                4.332e+01  3.030e+00  14.295  < 2e-16 ***
## COMMTYPEMajor Urban                   3.702e+01  8.124e+00   4.556 5.74e-06 ***
## COMMTYPENon-metropolitan Fast Growing 3.945e+01  4.020e+00   9.815  < 2e-16 ***
## COMMTYPENon-metropolitan Stable       3.651e+01  2.035e+00  17.940  < 2e-16 ***
## COMMTYPEOther Central City            3.719e+01  3.898e+00   9.540  < 2e-16 ***
## COMMTYPEOther Central City Suburban   3.827e+01  2.112e+00  18.117  < 2e-16 ***
## COMMTYPERural                         3.885e+01  1.704e+00  22.799  < 2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 19.49 on 1192 degrees of freedom
##   (5 observations deleted due to missingness)
## Multiple R-squared:  0.3465, Adjusted R-squared:  0.3416 
## F-statistic: 70.24 on 9 and 1192 DF,  p-value: < 2.2e-16
Distric_model<-lm(DZRVLOCP~DPETALLC+COMMTYPE,data =TEA_Data)
Distric_model<-lm(DZRVLOCP~DPETALLC+COMMTYPE,data =TEA_Data)
plot(Distric_model,which=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(Distric_model)
##  lag Autocorrelation D-W Statistic p-value
##    1       0.2530837      1.493002       0
##  Alternative hypothesis: rho != 0
library(tidyverse)
library(readxl)
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
bptest(Distric_model)
## 
##  studentized Breusch-Pagan test
## 
## data:  Distric_model
## BP = 118.25, df = 9, p-value < 2.2e-16
shapiro.test(Distric_model$residuals)
## 
##  Shapiro-Wilk normality test
## 
## data:  Distric_model$residuals
## W = 0.96612, p-value = 3.905e-16
plot(Distric_model,which=2)

kitchen_sink<-lm(DZRVLOCP~DPETALLC+COMMTYPE,data =TEA_Data)

vif(kitchen_sink)
##            GVIF Df GVIF^(1/(2*Df))
## DPETALLC 2.3955  1        1.547740
## COMMTYPE 2.3955  8        1.056118
pastecs::stat.desc(TEA_Data$DZRVLOCP)
##       nbr.val      nbr.null        nbr.na           min           max 
##  1202.0000000     8.0000000     5.0000000    -6.2000000    97.6000000 
##         range           sum        median          mean       SE.mean 
##   103.8000000 45584.3000000    35.3000000    37.9237105     0.6928507 
##  CI.mean.0.95           var       std.dev      coef.var 
##     1.3593323   577.0105864    24.0210447     0.6334044