setwd("I:\\classes\\statcomputingI.2012")
setwd("I:/classes/statcomputingI.2012")

data <- read.csv("SCBC2004.csv")

summary(data)
summary(data$stagen)

mean(data$stagen, na.rm=T)

q1 <- quantile(data$age, prob=c(0.025, 0.975))

age <- data$age
stagen <- data$stagen
site <- data$site

x <- cbind(age, stagen)
y <- data.frame(age, stagen)

y <- as.data.frame(x)

z <- cbind(site, age)
is.vector(age)

z <- c(1,2,3,4,5)

##################
# EXAMPLES OF CODE TO HELP WITH THE HOMEWORK

################
# Read in the dataset
setwd("I:/classes/statcomputingI")
data <- read.csv("SCBC2004.csv")

#######################
# what is the dimension of our dataset?

dim(data)

################
# what are the names of the variables in our dataset?
names(data)

################
# what are the mean, median, 1st and 3rd quartile of age?
age <- data$age
summary(age)
quantile(age)
quantile(age, prob=c(0.25, 0.75))

##########################
# create a boxplot of age
boxplot(age)

#########################
# create a histogram of age
hist(age)

########################
# generate a new variable that is the log of age
logage <- log(age)

#########################
# generate a new categorical version of age

agegrp <- cut(age, breaks=c(0,50,60,130))

#############################
# make a table of agegrp by er status

table(agegrp, data$ern)

##############################
# test that there is an association between age group
# and er status using fisher's test
tabi <- table(agegrp, data$ern)
fisher.test(tabi)

#########################
# test that there is an association between age and er using t-test
t.test(age~data$ern)