###########################################################################
# PUBLG100: Introduction to Quantitative Methods
#
# Week 4 Seminar: Bivariate linear regression models
#
#

# Set your working directory
#
# CAUTION: Make sure the directory you specify here matches the working directory on your computer.
#          We're using N:/PUBLG100 only for illustration purposes and it would only work if you're 
#          using a UCL dekstop. If you're using your own laptop, then replace N:/PUBLG100 with the 
#          appropriate directory (or folder)
setwd("N:/PUBLG100")


# Verify that your working directory is set correctly
getwd()


## ----eval = FALSE--------------------------------------------------------
## install.packages("Zelig")
## install.packages("texreg")

## ----message = FALSE-----------------------------------------------------
library(texreg)
library(Zelig)
library(dplyr)

## ------------------------------------------------------------------------
# clear environment
rm(list = ls())

# set working directory
# setwd(...)

## ----echo = FALSE--------------------------------------------------------
source("../common/knitr_hooks.R")

## ------------------------------------------------------------------------
# load the California test score datasets
CA_admin <- read.csv("CASchoolAdmin.csv")
CA_students <- read.csv("CAStudents.csv")

## ------------------------------------------------------------------------
names(CA_admin)
str(CA_admin)

## ------------------------------------------------------------------------
names(CA_students)
str(CA_students)

## ------------------------------------------------------------------------
# merge the two datasets
CA_schools <- merge(CA_admin, CA_students, by = c("county", "school"))

# explore dataset
names(CA_schools)

## ----eval = FALSE--------------------------------------------------------
## head(CA_schools)

## ------------------------------------------------------------------------
CA_schools <- mutate(CA_schools, 
                     STR = students / teachers,
                     score = (math + read) / 2)

## ------------------------------------------------------------------------
plot(score ~ STR, data = CA_schools,
     xlab = "Student-Teacher Ratio",
     ylab = "Test Score")

## ------------------------------------------------------------------------
STR_model <- lm(score ~ STR, data = CA_schools)

## ------------------------------------------------------------------------
summary(STR_model)

## ------------------------------------------------------------------------
plot(score ~ STR, data = CA_schools,
     xlab = "Student-Teacher Ratio",
     ylab = "Test Score")
abline(STR_model, col = "red")

## ------------------------------------------------------------------------
screenreg(STR_model)

## ------------------------------------------------------------------------
income_model <- lm(score ~ income, data = CA_schools)
summary(income_model)

## ------------------------------------------------------------------------
plot(score ~ income, data = CA_schools,
     xlab = "District Income",
     ylab = "Test Score")
abline(income_model, col = "blue")

## ------------------------------------------------------------------------
screenreg(list(STR_model, income_model))

## ------------------------------------------------------------------------
htmlreg(list(STR_model, income_model), file = "California_Schools.doc")

## ----message = FALSE-----------------------------------------------------
z.out <- zelig(score ~ income, data = CA_schools, model = "ls")

## ------------------------------------------------------------------------
summary(z.out)

## ------------------------------------------------------------------------
x.out <- setx(z.out, income = seq(min(CA_schools$income), max(CA_schools$income), 1))
s.out <- sim(z.out, x = x.out)

## ----out.lines=1:40------------------------------------------------------
summary(s.out)

## ------------------------------------------------------------------------
ci.plot(s.out, ci = 95, xlab = "District Income (in USD $1000)")