getwd()## [1] "/cloud/project"regression1<-read.csv("incidents.csv",header=T, sep = ",")
str(regression1)## 'data.frame': 16 obs. of 4 variables:
## $ area : chr "Boulder" "California-lexington" "Huntsville" "Seattle" ...
## $ zone : chr "west" "east" "east" "west" ...
## $ population: chr "107,353" "326,534" "444,752" "750,000" ...
## $ incidents : int 605 103 161 1703 1003 527 721 704 105 403 ...summary(regression1)## area zone population incidents
## Length:16 Length:16 Length:16 Min. : 103.0
## Class :character Class :character Class :character 1st Qu.: 277.8
## Mode :character Mode :character Mode :character Median : 654.0
## Mean : 695.2
## 3rd Qu.: 853.0
## Max. :2072.0pkg <- c("ggplot2", "scales", "maptools",
"sp", "maps", "grid", "car" )
new.pkg <- pkg[!(pkg %in% installed.packages())]
if (length(new.pkg)) {
install.packages(new.pkg)
}## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.5'
## (as 'lib' is unspecified)## Warning: package 'maptools' is not available for this version of R
##
## A version of this package for your version of R might be available elsewhere,
## see the ideas at
## https://cran.r-project.org/doc/manuals/r-patched/R-admin.html#Installing-packagesregression1$population <- as.numeric(gsub(",","",regression1$population))
regression1$population #changing the data type of population from a character to an integer## [1] 107353 326534 444752 750000 64403 2744878 1600000 2333000 1572816
## [10] 712091 6900000 2700000 4900000 4200000 5200000 7100000regression2<-regression1[,-1] #this makes a new data frame that deletes column 1head(regression2) #shows the filereg.fit1<-lm(regression1$incidents ~ regression1$population) #makes the first model
summary(reg.fit1) #fail to reject the null hypothesis, p-value is greater than 0.05##
## Call:
## lm(formula = regression1$incidents ~ regression1$population)
##
## Residuals:
## Min 1Q Median 3Q Max
## -684.5 -363.5 -156.2 133.9 1164.7
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.749e+02 2.018e+02 2.353 0.0337 *
## regression1$population 8.462e-05 5.804e-05 1.458 0.1669
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 534.9 on 14 degrees of freedom
## Multiple R-squared: 0.1318, Adjusted R-squared: 0.0698
## F-statistic: 2.126 on 1 and 14 DF, p-value: 0.1669#The population p-value is above to 5% significance level, it is not significant. The adjusted r-squared is low, at 0.0698.
reg.fit2<-lm(incidents ~ zone+population, data = regression1) #second model
summary(reg.fit2) #zone is significant##
## Call:
## lm(formula = incidents ~ zone + population, data = regression1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -537.21 -273.14 -57.89 188.17 766.03
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.612e+02 1.675e+02 0.962 0.35363
## zonewest 7.266e+02 1.938e+02 3.749 0.00243 **
## population 6.557e-05 4.206e-05 1.559 0.14300
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 384.8 on 13 degrees of freedom
## Multiple R-squared: 0.5828, Adjusted R-squared: 0.5186
## F-statistic: 9.081 on 2 and 13 DF, p-value: 0.003404#For model 2, zone west is significant t a 5% significance level, as its p-value is below 0.05. Population, though, is not significant because it is above the 5%. The adjusted r-squared is 0.5186.
regression2$zone <- ifelse(regression2$zone == "west", 1, 0) #isolating the zone west with the other zonesinteraction<-regression2$zone*regression2$population #trying to see the interaction between the zone and population in regression 2reg.fit3<-lm(regression1$incidents~interaction+regression1$population+regression1$zone)
#factoring in incidents
summary(reg.fit3)##
## Call:
## lm(formula = regression1$incidents ~ interaction + regression1$population +
## regression1$zone)
##
## Residuals:
## Min 1Q Median 3Q Max
## -540.91 -270.93 -59.56 187.99 767.99
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.659e+02 2.313e+02 0.717 0.4869
## interaction 2.974e-06 9.469e-05 0.031 0.9755
## regression1$population 6.352e-05 7.868e-05 0.807 0.4352
## regression1$zonewest 7.192e+02 3.108e+02 2.314 0.0392 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 400.5 on 12 degrees of freedom
## Multiple R-squared: 0.5829, Adjusted R-squared: 0.4786
## F-statistic: 5.589 on 3 and 12 DF, p-value: 0.01237#Population is not significant at a 5% significane level, because its p-value is well above 0.05.
#Zone is significant at a 5% significane level, because its p-value is below 0.05.
#Interaction is not significant at a 5% significance level, because its p-value is well above 0.05.
#The adjusted r-squared of the moodel is 0.4786.
reg.fit4<-lm(regression1$incidents~interaction)
summary(reg.fit4)##
## Call:
## lm(formula = regression1$incidents ~ interaction)
##
## Residuals:
## Min 1Q Median 3Q Max
## -650.28 -301.09 -83.71 123.23 1103.76
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.951e+02 1.320e+02 3.751 0.00215 **
## interaction 1.389e-04 4.737e-05 2.932 0.01093 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 451.9 on 14 degrees of freedom
## Multiple R-squared: 0.3804, Adjusted R-squared: 0.3361
## F-statistic: 8.595 on 1 and 14 DF, p-value: 0.01093#With interaction as the only feature, interaction is singificant as the p-value is under 0.05. The adjusted R-squared is 0.3361.
#Of the models ran, I would choose to run Reg.Fit2. This is because it has the highest adjusted r-squared at 0.5186, as well as the lowest p-values for zone west.