#######################################################
## calculator
2 + 3
4 * 2 / 13 + 7
result <- 2 + 3
print(result)
ls()

#######################################################
## variables
x <- 3
y <- 4
z <- x + y
print(z)

x <- c(1,2,3,4)
sum(x)
min(x)
max(x)

y <- c(5,6,7)
z <- c(x,y)
z <- 1:7

#######################################################
## getting data in and out and dataframes
load("state.Rda")
ls()
print(state)
names(state)
state$name
state$unemp
state$unifcont

state2 <- read.csv("state.csv")

#######################################################
## descriptive statistics
class.data <- c(1,3,4,4,5,10)

mean(class.data)
sd(class.data)
median(class.data)
quantile(class.data)
IQR(class.data)

mean(state$unemp)
sd(state$unemp)
median(state$unemp)
quantile(state$unemp)
IQR(state$unemp)

#######################################################
## histograms
par(mar=c(5.1, 4.1, 0.1, 0.1))
hist(state$unemp, freq=FALSE, main="", xlab="Unemployment Rate")
box()

#######################################################
## kernel density plots
plot(density(state$unemp), main="", xlab="Unemployment Rate")

#######################################################
## histograms with statistical control
par(mfrow=c(1,2), mar=c(5.1, 4.1, 0.1, 0.2))
hist(state$unemp[state$unifcont==1], freq=FALSE, main="",
   xlab="Unemployment Rate (Unified Control)", ylim=c(0,.45),
   xlim=c(2,9))
box()
hist(state$unemp[state$unifcont==0], freq=FALSE, main="",
   xlab="Unemployment Rate (Divided Government)", ylim=c(0,.45),
   xlim=c(2,9))
box()

#######################################################
## boxplots
par(mfrow=c(1,1), mar=c(0.1, 4.1, 0.1, 0.1))
boxplot(state$unemp, ylab="Unemployment Rate")

#######################################################
## frequency distribution and cross-tabulation
load("nes1996.Rda")
ls()
table(nes1996$pid)
table(nes1996$pid, nes1996$gender)

#######################################################
## Computing Normal Probabilities

## probability score between 73 to 87
pnorm(87, mean=80, sd=5) - pnorm(73, mean=80, sd=5)

## probability score between 71 to 86
pnorm(86, mean=80, sd=5) - pnorm(71, mean=80, sd=5)
pnorm(1.2) - pnorm(-1.8)