### Week 4: CLRM Problems
### Code from class

## analyze the clasic Anscombe dataset
(anscombe <-
 read.csv(url("http://www.kenbenoit.net/courses/quant2/anscombe.csv")))
round(apply(anscombe, 2, mean),2)   # same means for x, y
attach(anscombe)
round(coef(lm(y1~x1)), 2)           # same b0, b1
round(coef(lm(y2~x2)), 2)
round(coef(lm(y3~x3)), 2)
round(coef(lm(y4~x4)), 2)
round(summary(lm(y1~x1))$r.squared, 2)   # same R^2
round(summary(lm(y2~x2))$r.squared, 2)
round(summary(lm(y3~x3))$r.squared, 2)
round(summary(lm(y4~x4))$r.squared, 2)
# plot the four x-y pairs
par(mfrow=c(2,2), mar=c(4, 4, 1, 1)+0.1) # 4 plots in one graphic window
plot(x1,y1)
abline(lm(y1~x1), col="red", lty="dashed")
plot(x2,y2)
abline(lm(y2~x2), col="red", lty="dashed")
plot(x3,y3)
abline(lm(y3~x3), col="red", lty="dashed")
plot(x4,y4)
abline(lm(y4~x4), col="red", lty="dashed")
detach(anscombe)

## run the Marsh and Benoit 2008 regression and produce diagnostic plots
library(foreign)
dail <- read.dta("dail2002.dta")
m1 <- lm(votes1st ~ spend_total*incumb, data=dail)
par(mar=c(4, 4, 1, 1)+0.1)
plot(m1, which=1:6)

## Residual v. Fitted plots
# restrict the cases that are missing or cannot be logged
dail <- dail[complete.cases(dail$spend_total, dail$incumb, dail$votes1st)
             & is.finite(log(dail$spend_total)),]
# residual v. fitted plot for spending: logged spending
plot(lm(votes1st ~ log(spend_total)*incumb, data=dail), which=1)
# residual v. fitted plot for spending: logged votes
plot(lm(log(votes1st) ~ spend_total*incumb, data=dail), which=1)
# residual v. fitted plot for spending: logged votes and spending
plot(lm(log(votes1st) ~ log(spend_total)*incumb, data=dail), which=1)

## other graphs are created by one-line code from slides