# R para principiantes
# PUCE, Quito, 5-8 enero 2010
# Simon Queenborough

# JUEVES: clase 14

############ ANOVA ##################

# Recall, the t-test was used to test hypotheses about the means of two independent samples. For example, to test
# if there is a diFFerence between control and treatment groups. The method called analysis of variance (ANOVA)
# allows one to compare means for more than 2 independent samples.

x = c(4,3,4,5,2,3,4,5)
y = c(4,4,5,5,4,5,4,4)
z = c(3,4,2,4,5,5,4,4)
scores = data.frame(x,y,z)
boxplot(scores)


# Analysis of variance allows us to investigate if all the graders have the same mean. The R function to do the
# analysis of variance hypothesis test (oneway.test) requires the data to be in a different format. It wants to have the
# data with a single variable holding the scores, and a factor describing the grader or category. The stack command
# will do this for us:

scores = stack(scores) # look at scores if not clear
names(scores)
head(scores)

m <- aov(values ~ ind, data=scores)
summary(m)


# kruskal-wallis test # non-parametric

kruskal.test(values ~ ind, data=scores)



######## two-way anova #############

gr <- read.table("growth.txt", header=T)

barplot(tapply(gr$gain,list(gr$diet,gr$supplement),mean),
    beside=T,ylim=c(0,30),col=rainbow(3))

tapply(gain,list(diet,supplement),mean)

model<-aov(gain~diet*supplement, data=gr)
summary(model)

model2 <-aov(gain~diet+supplement, data=gr)
summary.lm(model2)

anova(model, model2)



########################################################################################
#
#   EJERCICIOS
#
########################################################################################

# 14.1
# The dataset InsectSpray has data on the count of insects in areas treated with one of 6 dierent types of
# sprays. The dataset is already in the proper format for the oneway analysis of variance { a vector with the
# data (count), and one with a factor describing the level (spray). First make a side-by-side boxplot to see if
# the means are equal. Then perform a oneway ANOVA to check if they are. Do they agree?