###############################################
## Author: Joshua M. Tebbs
## Date: 27 July 2016
## Update: 15 March 2024
## STAT 110 course notes: R Code Chapter 12
###############################################

# Example 12.1
# Page 102
# TTF data
# Enter data
TTF = c(0.8,7.5,13.4,1.4,0.5,68.9,16.1,20.4,15.6,4.2,2.4,8.2,5.3,14.0)
# Sort data from low to high
sort(TTF)
median(TTF) # median
quantile(TTF,type=2) # 5-number summary
# Make boxplot of the data (Figure 12.1)
boxplot(TTF,range=0,xlab="",ylab="Time until treatment failure (in months)",col="lightblue")
# Boxplot with outlier identified (Figure 12.2)
boxplot(TTF,range=1.5,xlab="",ylab="Time until treatment failure (in months)",col="lightblue")


# Example 12.2
# Page 107
# Arsenic data
# Enter data
arsenic = c(17.6,10.4,13.5,4,19.9,16,12,12.2,11.4,12.7,3,10.3,21.4,19.4,9,6.5,10.1,8.7,9.7,6.4,
	9.7,63,15.5,10.7,18.2,7.5,6.1,6.7,6.9,0.8,73.5,12,28,12.6,9.4,6.2,15.3,7.3,10.7,15.9,
	5.8,1,8.6,1.3,13.7,2.8,2.4,1.4,2.9,13.1,15.3,9.2,11.7,4.5,1,1.2,0.8,1,2.4,4.4,2.2,2.9,
	3.6,2.5,1.8,5.9,2.8,1.7,4.6,5.4,3,3.1,1.3,2.6,1.4,2.3,1,5.4,1.8,2.6,3.4,1.4,10.7,18.2,
	7.7,6.5,12.2,10.1,6.4,10.7,6.1,0.8,12,28.1,9.4,6.2,7.3,9.7,62.1,15.5,6.4,9.5)
# Histogram (Figure 12.3, left)
bins = seq(0,80,5)
hist(arsenic,breaks = bins,xlab="Arsenic concentration (pp billion)",ylab="Count",main="",col="lightblue")
# Boxplot (Figure 12.3, right)
boxplot(arsenic,range=0,xlab="",ylab="Arsenic concentration (pp billion)",col="lightblue")
quantile(arsenic,type=2) # 5-number summary


Example 12.3
# Page 108
# SSHA score data
# Enter data 
female = c(154,109,137,115,152,140,154,178,101,103,126,126,137,165,165,129,200,148)
male = c(108,140,114,91,180,115,126,92,169,146,109,132,75,88,113,151,70,115,187,104)

# Make boxplot of the data (Figure 12.4)
# You do not need to specify "range=1.5" option (this is the default value)
boxplot(female,male,xlab="",names=c("Female","Male"),ylab="SSHA score",col="lightblue")


# Figure 12.5
# Page 110
# Side-by-side boxplots of birth weight by nutrition type
# Read in data
nec = read.csv(file = "C:\\Users\\tebbs\\OneDrive - University of South Carolina\\Documents\\texfiles\\Collaboration\\Christina Piro\\Data\\Caffeine_data_updated_062811_CLEAN.csv", header=T)

# Extract birthweights according to which nutrition was used
breastmilk = nec$Birth.weight[which(nec$Nutrition==1)]
fluids = nec$Birth.weight[which(nec$Nutrition==2)]
TPN = nec$Birth.weight[which(nec$Nutrition==3)]
formula = nec$Birth.weight[which(nec$Nutrition==4)]
# Make boxplot of the data
boxplot(breastmilk,fluids,TPN,formula,xlab="",names=c("Breastmilk","Fluids","TPN","Formula"),ylab="Birth weight (in grams)",col="lightblue")


# Example 12.4
# Page 111
# Clay model data
# Enter data
indentation = c(22.6,25.9,34.9,35.6,45.4,46.5,47.7,49.4,50.7,51.3)
# Histogram (Figure 12.6)
hist(indentation,xlab="Deepest indentation (mm)",ylab="Count",main="",col="lightblue")
points(x=mean(indentation),y=0,pch=19,cex=1.5)
# "Dotchart" (Figure 12.7)
dotchart(indentation,xlab="Deepest indentation (mm)",ylab="Individual",lcolor="black")
abline(v=41,lty=2)
mean(indentation) # mean
sd(indentation) # standard devation


# Example 12.5
# Page 114
# Mice data
# Enter data
conventional = c(159,189,191,198,200,207,220,235,245,250,256,261,265,266,280,343,356,383,403,414,428,
	432,317,318,399,495,525,536,549,552,554,337,558,571,586,594,596,605,612,621,628,631,636,643,647,
	648,649,661,663,666,670,695,697,700,705,712,713,738,748,753,40,42,51,62,163,179,206,222,228,252,
	249,282,324,333,341,366,385,407,420,431,441,462,482,517,517,524,564,567,586,619,620,621,622,647,
	651,686,761,763,461)
germ.free = c(158,192,193,194,195,202,212,215,229,230,237,240,244,247,259,300,301,321,337,415, 
	434,444,485,496,529,537,624,707,800,430,590,606,638,655,679,691,693,696,747,752,760,778,
	821,986,136,246,255,376,421,565,516,517,652,655,658,660,662,675,681,734,736,737,757,769,
	777,800,807,825,855,857,864,868,870,870,873,882,895,910,934,942,1015,1019)
# Boxplots (Figure 12.8)
boxplot(conventional,germ.free,xlab="",names=c("Conventional","Germ-free"),ylab="Time to death (in days)",col="lightblue")
# Calculate mean and standard devation for each group
mean(conventional)
mean(germ.free)
sd(conventional)
sd(germ.free)


# Figure 12.9
# Page 118
# This is the same figure as above in Example 12.2 (Figure 12.3, left)