eurobarometer_trend.r

## eurobarometer_trend.r
### Starter script for analyzing the Eurobarometer Trend data (1970-2002).
### Outline:
### 1. Import the dataset straight from the web
### 2. Isolate variables of interest and clean them up
### 3. Estimate a regression model of what makes people turnout for EP elections

### Download packages we're going to use
install.packages("ggplot2")
install.packages("foreign")
install.packages("Zelig")
library(ggplot2)
library(foreign)
library(Zelig)

### Define the URL where the dataset is located
url<-"https://dl.dropboxusercontent.com/u/20498362/eurobarometer_trends/eurobarometer_trends.dta?raw=1"

### Read the dataset straight from the web, name the dataframe "data"
data <- read.dta(url)

### Variable "mediause" asks how much the respondent relies on the media.
summary(data$mediause) # Get a simple summary
data$mediause[data$mediause=="dk"]<-NA # Let's consider all the "dk" answerers as missing (NA)
data$mediause[data$mediause=="na"]<-NA # Let's consider all the "dk" as missing (NA)
data$mediause[data$mediause=="inap"]<-NA # Let's consider all the "inap" as missing (NA)
data$mediause<-factor(data$mediause) # this removes unused levels
levels(data$mediause)<-c("Very high", "High", "Low", "Very low") # Clean up the messy names of the levels
data$medianum<-as.numeric(data$mediause) # convert the categories to a numerical scale (cheating a bit!)
data$medianum<-(4 - data$medianum) # Subtract from 4 to make it more intuitive (higher number = more likely to vote)

### Variable "particip" asks respondent how likely they are to vote in the EP elections.
summary(data$particip)
data$particip[data$particip=="DK,NA"]<-NA
data$particip[data$particip=="depends"]<-NA
data$particip[data$particip=="inap"]<-NA
data$particip<-factor(data$particip)
levels(data$particip)<-c("Certainly yes", "Probably yes", "Probably not", "Certainly not")
data$participnum<-as.numeric(data$particip) # convert the categories to a numerical scale (cheating a bit!)
data$participnum<-(4 - data$participnum) # Subtract from 4 to make it more intuitive (higher number = more likely to vote)
data$particip <- ifelse(data$participnum>=2, 1, 0) # Collapse into a no/yes, 0/1, binary version

### Variable "income" asks the respondent's income level.
summary(data$income)

### Variable "polint" asks the respondent's political interest generally.
summary(data$polint)
data$polint[data$polint=="DK,NA"]<-NA
data$polint[data$polint=="inap"]<-NA
data$polint<-factor(data$polint)
levels(data$polint)<-c("A great deal", "To some extent", "Not much", "Not at all")
data$polintnum<-as.numeric(data$polint) # convert the categories to a numerical scale (cheating a bit!)
data$polintnum<-(4 - data$polintnum) # Subtract from 4 to make it more intuitive (higher number = more likely to vote)
summary(data$polintnum)

### Variable "ecint3" asks the respondent's interest in EU politics.
summary(data$ecint3)
data$ecint3[data$ecint3=="DK, NA"]<-NA
data$ecint3[data$ecint3=="inap"]<-NA
data$ecint3<-factor(data$ecint3)
levels(data$ecint3)<-c("Very interested", "A little", "Not at all")
data$ecint3num<-as.numeric(data$ecint3) # convert the categories to a numerical scale (cheating a bit!)
data$ecint3num<-(3 - data$ecint3num) # Subtract from 4 to make it more intuitive (higher number = more likely to vote)
summary(data$ecint3num)

### Variable "ecint4" asks the respondent's interest in EU politics.
summary(data$ecint4)
data$ecint4[data$ecint4=="DK, NA"]<-NA
data$ecint4[data$ecint4=="inap"]<-NA
data$ecint4<-factor(data$ecint4)
levels(data$ecint4)<-c("A great deal", "To some extent", "Not much", "Not at all")
data$ecint4num<-as.numeric(data$ecint4) # convert the categories to a numerical scale (cheating a bit!)
data$ecint4num<-(4 - data$ecint4num) # Subtract from 4 to make it more intuitive (higher number = more likely to vote)
summary(data$ecint4num)

### Variable "nation1" captures the respondent's nation
summary(data$nation1)
data$gb<-ifelse(data$nation1=="GREAT BRITAIN", 1, 0)

### Variable "year" captures the year of the survey
summary(data$year)

##########################################################################
### Zero in on the subset of the sample relevant to your research question
##########################################################################

# Subset the data to one country in one year because having multiple countries/years gets complicated statistically
dataUK1994<-subset(data, nation1=="GREAT BRITAIN" & data$year==1994, select=c("particip", "medianum", "polintnum", "income", "nation1"))

#########################################################################
### Always do some basic visual inspection / descriptive analysis of your key variables

qplot(dataUK1994$particip) +
  labs(x="Likely to vote in the EU Parliament election?")

qplot(dataUK1994$medianum) +
  labs(x="Degree of relying on the media")

#######################################################
####### Regression analysis using the Zelig package
#######################################################

# DV is likely to vote or not likely to vote, i.e. a binary variable.
# So we need a "logit" model

model<-zelig(particip ~
               income + medianum,
             data=dataUK1994,
             model="logit")

summary(model)


x.out <- setx(model, medianum=seq(0,3,1)) # Set media to a range from its min to its max
s.out <- sim(model, x = x.out)

ci.plot(s.out,
        main="Effect of Media on Probability of Voting in the European Election, UK in 1994")