library(MASS)
library(dplyr)
## 
## Attaching package: 'dplyr'
## The following object is masked from 'package:MASS':
## 
##     select
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats   1.0.1     ✔ readr     2.2.0
## ✔ ggplot2   4.0.3     ✔ stringr   1.6.0
## ✔ lubridate 1.9.5     ✔ tibble    3.3.1
## ✔ purrr     1.2.2     ✔ tidyr     1.3.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ✖ dplyr::select() masks MASS::select()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
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(car)
## Loading required package: carData
## 
## Attaching package: 'car'
## 
## The following object is masked from 'package:purrr':
## 
##     some
## 
## The following object is masked from 'package:dplyr':
## 
##     recode
library(pastecs)
## 
## Attaching package: 'pastecs'
## 
## The following object is masked from 'package:tidyr':
## 
##     extract
## 
## The following objects are masked from 'package:dplyr':
## 
##     first, last
cities <- read_xlsx("City_data.xlsx")
cities_clean <- cities |> select(year,tax_property_city,education_city,public_welfare_city,police_city,housing_commdevt_city)

cities_1977 <- cities_clean %>% filter(year == 1977)
cities_1987 <- cities_clean %>% filter(year == 1987)
cities_1997 <- cities_clean %>% filter(year == 1997)
cities_2007 <- cities_clean %>% filter(year == 2007)
cities_2017 <- cities_clean %>% filter(year == 2017)
summary(cities_1977)
##       year      tax_property_city education_city     public_welfare_city
##  Min.   :1977   Min.   :  27.5    Min.   :   0.000   Min.   :   0.00    
##  1st Qu.:1977   1st Qu.: 270.7    1st Qu.:   1.295   1st Qu.:   0.00    
##  Median :1977   Median : 418.5    Median :  29.540   Median :   0.00    
##  Mean   :1977   Mean   : 610.0    Mean   : 320.940   Mean   :  54.25    
##  3rd Qu.:1977   3rd Qu.: 646.3    3rd Qu.:  56.110   3rd Qu.:  10.29    
##  Max.   :1977   Max.   :3557.1    Max.   :3021.520   Max.   :2389.51    
##   police_city      housing_commdevt_city
##  Min.   :   2.05   Min.   :   0.000     
##  1st Qu.: 167.78   1st Qu.:   5.115     
##  Median : 216.83   Median :  50.370     
##  Mean   : 237.35   Mean   : 105.598     
##  3rd Qu.: 272.90   3rd Qu.: 135.765     
##  Max.   :1043.49   Max.   :1780.100
summary(cities_1987)
##       year      tax_property_city education_city    public_welfare_city
##  Min.   :1987   Min.   :  18.67   Min.   :   0.00   Min.   :   0.00    
##  1st Qu.:1987   1st Qu.: 243.10   1st Qu.:   0.00   1st Qu.:   0.00    
##  Median :1987   Median : 406.03   Median :  30.37   Median :   0.00    
##  Mean   :1987   Mean   : 561.59   Mean   : 318.42   Mean   :  45.65    
##  3rd Qu.:1987   3rd Qu.: 642.10   3rd Qu.:  68.84   3rd Qu.:  10.21    
##  Max.   :1987   Max.   :4415.05   Max.   :3237.24   Max.   :2345.46    
##   police_city     housing_commdevt_city
##  Min.   :   0.0   Min.   :   0.00      
##  1st Qu.: 198.2   1st Qu.:  36.72      
##  Median : 242.3   Median :  68.46      
##  Mean   : 273.6   Mean   : 120.78      
##  3rd Qu.: 310.9   3rd Qu.: 143.69      
##  Max.   :1542.2   Max.   :1188.63
summary(cities_1997)
##       year      tax_property_city education_city    public_welfare_city
##  Min.   :1997   Min.   :  42.48   Min.   :   0.00   Min.   :   0.00    
##  1st Qu.:1997   1st Qu.: 246.92   1st Qu.:   0.00   1st Qu.:   0.00    
##  Median :1997   Median : 417.50   Median :  30.30   Median :   0.00    
##  Mean   :1997   Mean   : 614.21   Mean   : 396.16   Mean   :  56.47    
##  3rd Qu.:1997   3rd Qu.: 676.73   3rd Qu.:  72.22   3rd Qu.:  10.28    
##  Max.   :1997   Max.   :4874.84   Max.   :3730.54   Max.   :3935.83    
##   police_city      housing_commdevt_city
##  Min.   :   0.07   Min.   :   0.00      
##  1st Qu.: 239.96   1st Qu.:  43.08      
##  Median : 305.17   Median :  85.82      
##  Mean   : 328.19   Mean   : 129.58      
##  3rd Qu.: 369.53   3rd Qu.: 167.57      
##  Max.   :1760.59   Max.   :1286.84
summary(cities_2007)
##       year      tax_property_city education_city    public_welfare_city
##  Min.   :2007   Min.   :   0.0    Min.   :   0.00   Min.   :   0.00    
##  1st Qu.:2007   1st Qu.: 343.8    1st Qu.:   0.00   1st Qu.:   0.00    
##  Median :2007   Median : 555.0    Median :  34.54   Median :   0.00    
##  Mean   :2007   Mean   : 747.1    Mean   : 530.67   Mean   :  60.40    
##  3rd Qu.:2007   3rd Qu.: 828.5    3rd Qu.:  79.30   3rd Qu.:  10.29    
##  Max.   :2007   Max.   :5511.4    Max.   :5379.66   Max.   :5565.58    
##   police_city      housing_commdevt_city
##  Min.   :  27.55   Min.   :   0.00      
##  1st Qu.: 294.75   1st Qu.:  45.12      
##  Median : 368.79   Median :  91.11      
##  Mean   : 401.59   Mean   : 144.59      
##  3rd Qu.: 441.84   3rd Qu.: 189.77      
##  Max.   :1466.31   Max.   :1155.68
summary(cities_2017)
##       year      tax_property_city education_city    public_welfare_city
##  Min.   :2017   Min.   :  36.52   Min.   :   0.00   Min.   :   0.00    
##  1st Qu.:2017   1st Qu.: 331.10   1st Qu.:   0.00   1st Qu.:   0.00    
##  Median :2017   Median : 523.42   Median :  29.99   Median :   0.00    
##  Mean   :2017   Mean   : 755.77   Mean   : 527.02   Mean   :  66.24    
##  3rd Qu.:2017   3rd Qu.: 816.14   3rd Qu.:  75.60   3rd Qu.:  10.47    
##  Max.   :2017   Max.   :4593.64   Max.   :5423.53   Max.   :6804.10    
##   police_city      housing_commdevt_city
##  Min.   :  21.49   Min.   :   0.00      
##  1st Qu.: 299.81   1st Qu.:  26.77      
##  Median : 380.69   Median :  61.97      
##  Mean   : 408.74   Mean   : 119.36      
##  3rd Qu.: 478.71   3rd Qu.: 112.14      
##  Max.   :1205.10   Max.   :1786.42
stat.desc(cities_1977$education_city)
##      nbr.val     nbr.null       nbr.na          min          max        range 
##    218.00000     46.00000      0.00000      0.00000   3021.52000   3021.52000 
##          sum       median         mean      SE.mean CI.mean.0.95          var 
##  69964.86000     29.54000    320.93972     44.33673     87.38576 428532.61937 
##      std.dev     coef.var 
##    654.62403      2.03971
stat.desc(cities_1987$education_city)
##      nbr.val     nbr.null       nbr.na          min          max        range 
## 2.180000e+02 6.100000e+01 0.000000e+00 0.000000e+00 3.237240e+03 3.237240e+03 
##          sum       median         mean      SE.mean CI.mean.0.95          var 
## 6.941656e+04 3.037000e+01 3.184246e+02 4.492732e+01 8.854979e+01 4.400252e+05 
##      std.dev     coef.var 
## 6.633439e+02 2.083206e+00
stat.desc(cities_1997$education_city)
##      nbr.val     nbr.null       nbr.na          min          max        range 
## 2.180000e+02 7.000000e+01 0.000000e+00 0.000000e+00 3.730540e+03 3.730540e+03 
##          sum       median         mean      SE.mean CI.mean.0.95          var 
## 8.636208e+04 3.030500e+01 3.961563e+02 5.740698e+01 1.131467e+02 7.184324e+05 
##      std.dev     coef.var 
## 8.476039e+02 2.139569e+00
stat.desc(cities_2007$education_city)
##      nbr.val     nbr.null       nbr.na          min          max        range 
## 2.180000e+02 7.300000e+01 0.000000e+00 0.000000e+00 5.379660e+03 5.379660e+03 
##          sum       median         mean      SE.mean CI.mean.0.95          var 
## 1.156857e+05 3.454000e+01 5.306685e+02 7.972859e+01 1.571416e+02 1.385749e+06 
##      std.dev     coef.var 
## 1.177179e+03 2.218294e+00
stat.desc(cities_2017$education_city)
##      nbr.val     nbr.null       nbr.na          min          max        range 
## 2.180000e+02 7.700000e+01 0.000000e+00 0.000000e+00 5.423530e+03 5.423530e+03 
##          sum       median         mean      SE.mean CI.mean.0.95          var 
## 1.148911e+05 2.999000e+01 5.270233e+02 8.137217e+01 1.603810e+02 1.443472e+06 
##      std.dev     coef.var 
## 1.201446e+03 2.279682e+00
stat.desc(cities_1977$tax_property_city)
##      nbr.val     nbr.null       nbr.na          min          max        range 
## 2.180000e+02 0.000000e+00 0.000000e+00 2.750000e+01 3.557140e+03 3.529640e+03 
##          sum       median         mean      SE.mean CI.mean.0.95          var 
## 1.329720e+05 4.184600e+02 6.099634e+02 3.929111e+01 7.744107e+01 3.365466e+05 
##      std.dev     coef.var 
## 5.801264e+02 9.510838e-01
stat.desc(cities_1987$tax_property_city)
##      nbr.val     nbr.null       nbr.na          min          max        range 
## 2.180000e+02 0.000000e+00 0.000000e+00 1.867000e+01 4.415050e+03 4.396380e+03 
##          sum       median         mean      SE.mean CI.mean.0.95          var 
## 1.224263e+05 4.060300e+02 5.615884e+02 3.718417e+01 7.328837e+01 3.014204e+05 
##      std.dev     coef.var 
## 5.490177e+02 9.776157e-01
stat.desc(cities_1997$tax_property_city)
##      nbr.val     nbr.null       nbr.na          min          max        range 
## 2.180000e+02 0.000000e+00 0.000000e+00 4.248000e+01 4.874840e+03 4.832360e+03 
##          sum       median         mean      SE.mean CI.mean.0.95          var 
## 1.338976e+05 4.174950e+02 6.142092e+02 4.327397e+01 8.529110e+01 4.082347e+05 
##      std.dev     coef.var 
## 6.389325e+02 1.040252e+00
stat.desc(cities_2007$tax_property_city)
##      nbr.val     nbr.null       nbr.na          min          max        range 
## 2.180000e+02 1.000000e+00 0.000000e+00 0.000000e+00 5.511430e+03 5.511430e+03 
##          sum       median         mean      SE.mean CI.mean.0.95          var 
## 1.628695e+05 5.549750e+02 7.471079e+02 4.893462e+01 9.644800e+01 5.220222e+05 
##      std.dev     coef.var 
## 7.225110e+02 9.670772e-01
stat.desc(cities_2017$tax_property_city)
##      nbr.val     nbr.null       nbr.na          min          max        range 
## 2.180000e+02 0.000000e+00 0.000000e+00 3.652000e+01 4.593640e+03 4.557120e+03 
##          sum       median         mean      SE.mean CI.mean.0.95          var 
## 1.647572e+05 5.234200e+02 7.557671e+02 5.151576e+01 1.015353e+02 5.785443e+05 
##      std.dev     coef.var 
## 7.606210e+02 1.006423e+00
cities_model77 <- lm(tax_property_city~education_city+public_welfare_city+police_city+housing_commdevt_city,data=cities_1977)
summary(cities_model77)
## 
## Call:
## lm(formula = tax_property_city ~ education_city + public_welfare_city + 
##     police_city + housing_commdevt_city, data = cities_1977)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -1385.20  -176.26   -40.67   133.62  1421.52 
## 
## Coefficients:
##                        Estimate Std. Error t value Pr(>|t|)    
## (Intercept)           250.53238   61.95305   4.044 7.35e-05 ***
## education_city          0.68837    0.03912  17.597  < 2e-16 ***
## public_welfare_city    -0.04617    0.11740  -0.393   0.6945    
## police_city             0.53037    0.24740   2.144   0.0332 *  
## housing_commdevt_city   0.14323    0.13428   1.067   0.2873    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 344.8 on 213 degrees of freedom
## Multiple R-squared:  0.6532, Adjusted R-squared:  0.6467 
## F-statistic: 100.3 on 4 and 213 DF,  p-value: < 2.2e-16
plot(cities_model77,which=1)

plot(cities_model77,which=2)

plot(cities_model77,which=3)

durbinWatsonTest(cities_model77)
##  lag Autocorrelation D-W Statistic p-value
##    1       0.2739975      1.433816       0
##  Alternative hypothesis: rho != 0
bptest(cities_model77)
## 
##  studentized Breusch-Pagan test
## 
## data:  cities_model77
## BP = 75.637, df = 4, p-value = 1.461e-15
vif(cities_model77)
##        education_city   public_welfare_city           police_city 
##              1.196961              1.421523              1.290340 
## housing_commdevt_city 
##              1.034912
cities_model77_changed<-lm(sqrt(tax_property_city)~sqrt(education_city)+sqrt(public_welfare_city)+sqrt(police_city)+sqrt(housing_commdevt_city),data=cities_1977)
durbinWatsonTest(cities_model77_changed)
##  lag Autocorrelation D-W Statistic p-value
##    1       0.4050859      1.184583       0
##  Alternative hypothesis: rho != 0
plot(cities_model77_changed,which=1)

plot(cities_model77_changed,which=2)

plot(cities_model77_changed,which=3)

bptest(cities_model77_changed)
## 
##  studentized Breusch-Pagan test
## 
## data:  cities_model77_changed
## BP = 27.72, df = 4, p-value = 1.421e-05
cities_model87 <- lm(tax_property_city~education_city+public_welfare_city+police_city+housing_commdevt_city,data=cities_1987)
summary(cities_model87)
## 
## Call:
## lm(formula = tax_property_city ~ education_city + public_welfare_city + 
##     police_city + housing_commdevt_city, data = cities_1987)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -791.82 -205.43  -10.65  133.25 1895.51 
## 
## Coefficients:
##                        Estimate Std. Error t value Pr(>|t|)    
## (Intercept)           -43.91189   56.64797  -0.775    0.439    
## education_city          0.47880    0.03910  12.247  < 2e-16 ***
## public_welfare_city     0.05248    0.14530   0.361    0.718    
## police_city             1.62805    0.18387   8.855 3.32e-16 ***
## housing_commdevt_city   0.04298    0.18174   0.236    0.813    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 342.5 on 213 degrees of freedom
## Multiple R-squared:  0.618,  Adjusted R-squared:  0.6108 
## F-statistic: 86.15 on 4 and 213 DF,  p-value: < 2.2e-16
plot(cities_model87,which=1)

plot(cities_model87,which=2)

plot(cities_model87,which=3)

durbinWatsonTest(cities_model87)
##  lag Autocorrelation D-W Statistic p-value
##    1       0.4288402       1.11578       0
##  Alternative hypothesis: rho != 0
bptest(cities_model87)
## 
##  studentized Breusch-Pagan test
## 
## data:  cities_model87
## BP = 85.358, df = 4, p-value < 2.2e-16
vif(cities_model87)
##        education_city   public_welfare_city           police_city 
##              1.244188              1.591575              1.200765 
## housing_commdevt_city 
##              1.275819
cities_model87_changed<-lm(sqrt(tax_property_city)~sqrt(education_city)+sqrt(public_welfare_city)+sqrt(police_city)+sqrt(housing_commdevt_city),data=cities_1987)
plot(cities_model87_changed,which=1)

plot(cities_model87_changed,which=2)

plot(cities_model87_changed,which=3)

durbinWatsonTest(cities_model87_changed)
##  lag Autocorrelation D-W Statistic p-value
##    1       0.5191628     0.9531299       0
##  Alternative hypothesis: rho != 0
bptest(cities_model87_changed)
## 
##  studentized Breusch-Pagan test
## 
## data:  cities_model87_changed
## BP = 28.212, df = 4, p-value = 1.13e-05
cities_model97 <- lm(tax_property_city~education_city+public_welfare_city+police_city+housing_commdevt_city,data=cities_1997)
summary(cities_model97)
## 
## Call:
## lm(formula = tax_property_city ~ education_city + public_welfare_city + 
##     police_city + housing_commdevt_city, data = cities_1997)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -1317.76  -228.84   -39.57   162.72  2249.50 
## 
## Coefficients:
##                        Estimate Std. Error t value Pr(>|t|)    
## (Intercept)           -36.35314   69.58423  -0.522    0.602    
## education_city          0.47042    0.03579  13.144  < 2e-16 ***
## public_welfare_city     0.05400    0.10775   0.501    0.617    
## police_city             1.48659    0.19798   7.509 1.61e-12 ***
## housing_commdevt_city  -0.20631    0.20345  -1.014    0.312    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 416.7 on 213 degrees of freedom
## Multiple R-squared:  0.5826, Adjusted R-squared:  0.5748 
## F-statistic: 74.33 on 4 and 213 DF,  p-value: < 2.2e-16
plot(cities_model97,which=1)

plot(cities_model97,which=2)

plot(cities_model97,which=3)

durbinWatsonTest(cities_model97)
##  lag Autocorrelation D-W Statistic p-value
##    1       0.4154871      1.167328       0
##  Alternative hypothesis: rho != 0
bptest(cities_model97)
## 
##  studentized Breusch-Pagan test
## 
## data:  cities_model97
## BP = 72.555, df = 4, p-value = 6.55e-15
vif(cities_model97)
##        education_city   public_welfare_city           police_city 
##              1.150409              1.280063              1.187908 
## housing_commdevt_city 
##              1.174920
cities_model97_changed<-lm(sqrt(tax_property_city)~sqrt(education_city)+sqrt(public_welfare_city)+sqrt(police_city)+sqrt(housing_commdevt_city),data=cities_1997)
plot(cities_model97_changed,which=1)

plot(cities_model97_changed,which=2)

plot(cities_model97_changed,which=3)

durbinWatsonTest(cities_model97_changed)
##  lag Autocorrelation D-W Statistic p-value
##    1       0.4774381      1.040648       0
##  Alternative hypothesis: rho != 0
bptest(cities_model97_changed)
## 
##  studentized Breusch-Pagan test
## 
## data:  cities_model97_changed
## BP = 27.218, df = 4, p-value = 1.796e-05
cities_model07 <- lm(tax_property_city~education_city+public_welfare_city+police_city+housing_commdevt_city,data=cities_2007)
summary(cities_model07)
## 
## Call:
## lm(formula = tax_property_city ~ education_city + public_welfare_city + 
##     police_city + housing_commdevt_city, data = cities_2007)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -1482.3  -258.9   -50.7   144.1  3304.8 
## 
## Coefficients:
##                       Estimate Std. Error t value Pr(>|t|)    
## (Intercept)           31.30764   84.10430   0.372   0.7101    
## education_city         0.34251    0.02884  11.878  < 2e-16 ***
## public_welfare_city    0.14316    0.09703   1.475   0.1416    
## police_city            1.12857    0.22129   5.100  7.5e-07 ***
## housing_commdevt_city  0.49915    0.26415   1.890   0.0602 .  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 477.8 on 213 degrees of freedom
## Multiple R-squared:  0.5707, Adjusted R-squared:  0.5626 
## F-statistic: 70.79 on 4 and 213 DF,  p-value: < 2.2e-16
plot(cities_model07,which=1)

plot(cities_model07,which=2)

plot(cities_model07,which=3)

durbinWatsonTest(cities_model07)
##  lag Autocorrelation D-W Statistic p-value
##    1       0.2702364      1.451296       0
##  Alternative hypothesis: rho != 0
bptest(cities_model07)
## 
##  studentized Breusch-Pagan test
## 
## data:  cities_model07
## BP = 51.23, df = 4, p-value = 1.998e-10
vif(cities_model07)
##        education_city   public_welfare_city           police_city 
##              1.095129              1.415018              1.490881 
## housing_commdevt_city 
##              1.717106
cities_model07_changed<-lm(sqrt(tax_property_city)~sqrt(education_city)+sqrt(public_welfare_city)+sqrt(police_city)+sqrt(housing_commdevt_city),data=cities_2007)
plot(cities_model07_changed,which=1)

plot(cities_model07_changed,which=2)

plot(cities_model07_changed,which=3)

durbinWatsonTest(cities_model07_changed)
##  lag Autocorrelation D-W Statistic p-value
##    1       0.3894611      1.210991       0
##  Alternative hypothesis: rho != 0
bptest(cities_model07_changed)
## 
##  studentized Breusch-Pagan test
## 
## data:  cities_model07_changed
## BP = 15.014, df = 4, p-value = 0.004673
cities_model17 <- lm(tax_property_city~education_city+public_welfare_city+police_city+housing_commdevt_city,data=cities_2017)
summary(cities_model17)
## 
## Call:
## lm(formula = tax_property_city ~ education_city + public_welfare_city + 
##     police_city + housing_commdevt_city, data = cities_2017)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -1887.36  -255.02   -39.54   187.78  2263.12 
## 
## Coefficients:
##                        Estimate Std. Error t value Pr(>|t|)    
## (Intercept)           164.97339   91.06989   1.812  0.07147 .  
## education_city          0.36046    0.03028  11.903  < 2e-16 ***
## public_welfare_city     0.25028    0.09033   2.771  0.00609 ** 
## police_city             0.86192    0.21718   3.969 9.88e-05 ***
## housing_commdevt_city   0.26759    0.20606   1.299  0.19549    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 501.1 on 213 degrees of freedom
## Multiple R-squared:  0.5739, Adjusted R-squared:  0.5659 
## F-statistic: 71.73 on 4 and 213 DF,  p-value: < 2.2e-16
plot(cities_model17,which=1)

plot(cities_model17,which=2)

plot(cities_model17,which=3)

durbinWatsonTest(cities_model17)
##  lag Autocorrelation D-W Statistic p-value
##    1          0.2422      1.508341       0
##  Alternative hypothesis: rho != 0
bptest(cities_model17)
## 
##  studentized Breusch-Pagan test
## 
## data:  cities_model17
## BP = 48.005, df = 4, p-value = 9.415e-10
vif(cities_model17)
##        education_city   public_welfare_city           police_city 
##              1.143862              1.676622              1.209420 
## housing_commdevt_city 
##              1.672429
cities_model17_changed<-lm(sqrt(tax_property_city)~sqrt(education_city)+sqrt(public_welfare_city)+sqrt(police_city)+sqrt(housing_commdevt_city),data=cities_2017)
plot(cities_model17_changed,which=1)

plot(cities_model17_changed,which=2)

plot(cities_model17_changed,which=3)

durbinWatsonTest(cities_model17_changed)
##  lag Autocorrelation D-W Statistic p-value
##    1       0.3628853       1.26271       0
##  Alternative hypothesis: rho != 0
bptest(cities_model17_changed)
## 
##  studentized Breusch-Pagan test
## 
## data:  cities_model17_changed
## BP = 24.848, df = 4, p-value = 5.396e-05