#Working Directory
getwd()
[1] "/cloud/project"
#if not installed than install specific packages #if installed, ignore
# make sure the packages for this chapter
# are installed, install if necessary
pkg <- 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/4.3’
(as ‘lib’ is unspecified)
Warning in install.packages :
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-packages
#Read CSV for Data #Header = True
# read the CSV with headers
regression1<-read.csv("incidents (5).csv", header=T,sep =",")
#comment out to download #Viewing Dataset
#View(regression1)
#summary of the amount of the data #note it didn’t break it down into east and west yet #This just shows the total number of zones, but fails to show the actual Population
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. :2072.0
#shows data points more detailed and structured #Seeing how our data is characterized
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 ...
#This is very important #Looking closely at the dataset there is comma’s, R can’t properly handle that in a numeric function. I actually didn’t catch that at first, was trying to figure it out on my own #I assume this is why the numbers did not populate in the initial summary #So this function removes the commas from the data, therefore making it numeric for R
regression1$population <- as.numeric(gsub(",","",regression1$population))
regression1$population
[1] 107353 326534 444752 750000 64403 2744878 1600000 2333000 1572816 712091
[11] 6900000 2700000 4900000 4200000 5200000 7100000
#We can see the commas are removed
str(regression1$population)
num [1:16] 107353 326534 444752 750000 64403 ...
#Removal of area #It will not just be categorized as zoning #either east or west #Important to note, the dataset has east and west in it we didn’t add it in the code
regression2<-regression1[,-1]#new data frame with the deletion of column 1
#showcasing the new dataset appearence with a header #still not exactly organized, but it does show the clear difference of east and west
head(regression2)
reg.fit1<-lm(regression1$incidents ~ regression1$population)
#summarizing the correlation between incidients and population
summary(reg.fit1)
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$population 8.462e-05 5.804e-05 1.458 0.1669
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Residual standard error: 534.9 on 14 degrees of freedom
Multiple R-squared: 0.1318, Adjusted R-squared: 0.0698
F-statistic: 2.126 on 1 and 14 DF, p-value: 0.1669
Based on the output obtained above, please answer the following question:
Is Population significant at a 5% significance level? What is the adjusted-R squared of the model? #The population is not significant in this instance at a 5% level #The R Squared is 0.13. The Adjusted R Sq is 0.0698 #This is very low as is, but the adjusted R being nearly half of r squared, is certainly not good
reg.fit2<-lm(incidents ~ zone+population, data = regression1)
#Pop v Zone v Incidents
summary(reg.fit2)
Call:
lm(formula = incidents ~ zone + population, data = regression1)
Residuals:
Min 1Q Median 3Q Max
-537.21 -273.14 -57.89 188.17 766.03
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 1.612e+02 1.675e+02 0.962 0.35363
zonewest 7.266e+02 1.938e+02 3.749 0.00243 **
population 6.557e-05 4.206e-05 1.559 0.14300
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Residual standard error: 384.8 on 13 degrees of freedom
Multiple R-squared: 0.5828, Adjusted R-squared: 0.5186
F-statistic: 9.081 on 2 and 13 DF, p-value: 0.003404
Based on the output obtained above, please answer the following question:
Are Population and/or Zone significant at a 5% significance level? What is the adjusted-R squared of the model? #Population is not significant, while ZoneWest Is significant at a 5% level. #The R Squared, is 0.5828, while the Adjusted is 0.5186. #The R Sq is better now, and the adjusted is closer
#This is simply stating if it is labeled west than it is 1, if not than it is 0 #so it can be broken up into east and west
regression1$zone <- ifelse(regression1$zone == "west", 1, 0)#Please explain the syntax and the output
#viewing the dataset, commented out
#View(regression1)
#viewing the structure #note the area is back in the dataset
str(regression1)
'data.frame': 16 obs. of 4 variables:
$ area : chr "Boulder" "California-lexington" "Huntsville" "Seattle" ...
$ zone : num 1 0 0 1 1 0 1 1 0 0 ...
$ population: num 107353 326534 444752 750000 64403 ...
$ incidents : int 605 103 161 1703 1003 527 721 704 105 403 ...
#regression1$zone<-as.integer((regression1$zone),replace=TRUE) was not necessary
#Creating a new indicator
interaction<-regression1$zone*regression1$population
#Explain the syntax
reg.fit3<-lm(regression1$incidents~interaction+regression1$population+regression1$zone)
#summary of all the data’s
summary(reg.fit3)
Call:
lm(formula = regression1$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$population 6.352e-05 7.868e-05 0.807 0.4352
regression1$zone 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
Based on the output obtained above, please answer the following question:
Is Population significant at a 5% significance level?
#It is not significant Is Zone significant at a 5% significance level? #
it is significant Is the interaction term significant at a 5%
significance level? #It is not significant What is the adjusted-R
squared of the model? #the R is 0.5829, which is “good” based off what
we said in class #the Adjusted is 0.4786, which is a farily big
difference in the two numbers
Let us now run a model where the only feature is the interaction term.
Is the interaction term significant at a 5% significance level? What is the adjusted-R squared of the model?
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
#The number is significant in this instrance
Which of the models run above would you choose to make predictions? Why?? #I would choose to start by comparing zone’s to incidents #than I would look at the population in the zone’s as a whole compared to incidents #Lastly, if you wanted too, you could jump into the zone specifically and locate which area’s have the most incidents per capita