library(faraway)
data(gavote)
help(gavote)

# introducing the data

head(gavote)
str(gavote)
summary(gavote)

gavote$undercount=(gavote$ballots-gavote$votes)/gavote$ballots
summary(gavote$undercount)

# not the same as
with(gavote,sum(ballots-votes)/sum(ballots))

# graphical and summary statistics

hist(gavote$undercount, main='Undercount',xlab='Proportion Undercount')

hist(gavote$undercount, main='Undercount',xlab='Proportion Undercount',breaks=20)
# same with a larger number of bins

plot(density(gavote$undercount),main='Undercount')
rug(gavote$undercount)

pie(table(gavote$equip))

barplot(sort(table(gavote$equip),decreasing=TRUE),las=2)

gavote$pergore = gavote$gore/gavote$votes
plot(pergore ~ perAA, gavote, xlab='Proportion African Americans',ylab='Proportion for Gore')

plot(undercount~equip, gavote, xlab='', las=3)

xtabs(~atlanta+rural,gavote)

names(gavote)[4]='usage'

nix=c(3,10,11,12)
cor(gavote[,nix])

# introducing linear models for this dataset

lmod=lm(undercount~pergore+perAA,gavote)
coef(lmod)

# could summarize results by
summary(lmod)

# or alternatively extract specific features of the model fit by the following sequence of commands

predict(lmod)
residuals(lmod)

predict(lmod,se.fit=T)

deviance(lmod)

df.residual(lmod)

nrow(gavote)-length(coef(lmod))

sqrt(deviance(lmod)/df.residual(lmod))

lmodsum=summary(lmod)

lmodsum$sigma

lmodsum$r.squared

cor(predict(lmod),gavote$undercount)^2

lmodsum$adj.r.squared

# A simplified form of the "summary" comment (specific to the faraway package) is this:
sumary(lmod)

# first look at the NOrth Carolina dataset
Y=read.csv('C:/Users/rsmith/jan16/UNC/STOR556/Data/ProportionNotReturned.csv',header=T)

hist(Y$PNR,main='Proportion Absentee Ballots Not Returned - NC Nov 2018')
plot(density(Y$PNR),main='Proportion Absentee Ballots Not Returned - NC Nov 2018')
rug(Y$PNR)