[SOLVED] CS # BS1033 Lecture 2 Analysis

# BS1033 Lecture 2 Analysis
# Author: Chris Hansman
# Email: [email protected]
# Date : 18/01/21

# Installing Packages
#install.packages(tidyverse)

# Loading Libraries
library(tidyverse)

#Loading Todays Data
#Reading Data
modes<-read_csv(“modes_experiment.csv”)votes<-read_csv(“votes_income.csv”)#————————————————–## Analyzing Candy Experiment#————————————————–## Plotting a comparison of means (ugly)ggplot(data=modes, aes(x=D_i, y=y_i)) +geom_bar(stat=”summary”, fun=”mean”)# Plotting a comparison of means (a bit prettier)ggplot(data=modes, aes(x=as.factor(D_i), y=y_i)) +geom_bar(stat=”summary”, fun.y=”mean”, width=0.5)+labs(x = “Treatment: Candy or Not”, y= “Modes Score”)+ylim(0,5) +ggsave(“modes_means.pdf”)#Conditional Means:modes %>%
group_by(D_i) %>%
summarize(mean(y_i))

# A T-test
ttest <- t.test(y_i~D_i, data=modes, var.equal=TRUE)ttest#Regressions To Recover Means:ols_modes<-lm(y_i~D_i, data= modes)summary(ols_modes)#————————————————–## Analyzing VotingData#————————————————–##Plotting All Dataggplot(data = votes ) + geom_point(aes(x = income, y = repvotes)) +geom_smooth(aes(x = income, y = repvotes), method=’lm’,formula=y~x)+ggsave(“votes_all.pdf”)#Plotting Data by Groupggplot(data = votes ) + geom_point(aes(x = income, y = repvotes, color=as.factor(south))) +geom_smooth(aes(x = income, y = repvotes, group=as.factor(south)), method=’lm’,formula=y~x) +ggsave(“votes_bygroup.pdf”)#Regressions Overall:ols_votes_all<-lm(repvotes~income, data= votes)summary(ols_votes_all)#Regressions For South:ols_votes_south<-lm(repvotes~income, data=subset(votes,south==1))summary(ols_votes_south)#Regressions For north:ols_votes_north<-lm(repvotes~income, data=subset(votes,south==0))summary(ols_votes_north) # The average of the two…(0.2968+0.3835 )/2#Regressions With Control:ols_votes_control<-lm(repvotes~income+south, data= votes)summary(ols_votes_control)