###############################################
## Author: Joshua M. Tebbs
## Date: 27 July 2016
## Update: 15 March 2024
## STAT 110 course notes: R Code Chapter 11
###############################################

# Figure 11.1
# Page 92
# Find data web site
# Cut and paste data set into a notepad file
# Save this file (e.g., birthweights.txt) to a folder on your laptop or desktop
# Import the data from the folder 

# This creates a table (with each row corresponding to one infant)
birth.weights = read.table("C:\\Users\\tebbs\\OneDrive - University of South Carolina\\Documents\\texfiles\\Classes\\USC\\stat110\\s24\\data\\birthweights.txt",header=TRUE)

# This creates a univariate data set (ignoring infant case number)
birth.weights = birth.weights[,1] # extracts data from the table

# Make histogram of the data
hist(birth.weights,xlab="Birth weight (in grams)",ylab="Count",main="",col="lightblue",ylim=c(0,120))


# Figure 11.2
# Page 93
# Birthweight data
# Change interval (class/bin) widths
# Figure 11.2 (left) # interval width = 100 grams
bins = seq(0,6000,100) 
hist(birth.weights,breaks=bins,xlab="Birth weight (in grams)",ylab="Count",main="",col="lightblue")
# Figure 11.2 (right) # interval width = 2000 grams
bins = seq(0,6000,2000)
hist(birth.weights,breaks=bins,xlab="Birth weight (in grams)",ylab="Count",main="",col="lightblue")


# Figure 11.3
# Page 94
# Birthweight data
# Make histogram of the data
hist(birth.weights,prob=TRUE,xlab="Birth weight (in grams)",ylab="Density",main="",col="lightblue")
# Add estimate of population density curve
lines(density(birth.weights),col="red",lwd=2)


# Figure 11.4
# Page 96
# Find data web site
# Cut and paste data set into a notepad file
# Save this file (e.g., bmi.txt) to a folder on your laptop or desktop
# Import the data from the folder 

# This creates a table (with each row corresponding to one child)
bmi = read.table("C:\\Users\\tebbs\\OneDrive - University of South Carolina\\Documents\\texfiles\\Classes\\USC\\stat110\\s24\\data\\bmi.txt",header=TRUE)
bmi = bmi[,1]

# Make histogram of the data (left)
bins = seq(0,50,2.5) # select intervals and lengths
hist(bmi,breaks=bins,xlab="Body mass index",ylab="Count",main="",col="lightblue",xlim=c(0,50),ylim=c(0,100))
# Add estimate of population density curve (right)
hist(bmi,prob=TRUE,breaks=bins,xlab="Body mass index",ylab="Density",main="",col="lightblue",xlim=c(0,50),ylim=c(0,0.125))
lines(density(bmi),col="red",lwd=2)


# Figure 11.5
# Page 97
# Construct histogram of IQ data (simulated)
IQ = rnorm(2200,100,15)
# Make histogram of the data (left)
bins = seq(40,160,5)
hist(IQ,breaks=bins,xlab="IQ score",ylab="Count",main="",col="lightblue")
# Add estimate of population density curve (right)
hist(IQ,prob=TRUE,breaks=bins,xlab="IQ score",ylab="Density",main="",col="lightblue")
lines(sort(IQ),dnorm(sort(IQ),mean(IQ),sd(IQ)),col="red",lwd=2)


# Figure 11.6
# Page 98
# Long jump distance data
# Enter data
distance = c(8.11,8.11,8.09,8.08,8.06,8.03,8.02,7.99,7.99,7.97,7.95,7.92,7.92,7.92,7.89,
	7.87,7.84,7.79,7.79,7.77,7.76,7.72,7.71,7.66,7.62,7.61,7.59,7.55,7.53,7.50,7.50,7.42,
	7.38,7.38,7.26,7.25,7.08,6.96,6.84,6.55)
# Make histogram of the data
bins = seq(6.0,8.6,0.2)
hist(distance,breaks = bins, xlab="Distance (in meters)",ylab="Count",main="",col="lightblue")


# Figure 11.7
# Page 99
# Old Faithful geyser data
# These data are available in R
data(faithful)
faithful = faithful[,2]
# Make histogram of the data
hist(faithful,prob=TRUE,xlab="Time between eruptions (in minutes)",ylab="Density ",main="",col="lightblue")
# Add estimate of population density curve
lines(density(faithful),col="red",lwd=2)


# Figure 11.8
# Page 101
# OSU final exam data
# Enter data
final.exam = c(95,98,93,91,95,90,90,96,98,89,93,92,88,79,91,83,85,90,81,87,79,87,
	88,83,86,80,77,81,81,78,79,82,78,76,79,76,73,81,78,84,70,71,77,65,69,70,63,77,74,
	82,69,74,67,44,63,70,57,63,51,52,22,57,47,54,52,76)
# Make stem plot of the data (Page 100)
stem(final.exam)
# Make histogram of the data (Page 101)
bins = seq(20,100,5)
hist(final.exam,breaks=bins,xlab="Final exam score",ylab="Count",main="",col="lightblue")
# Make stem plot of the data (Page 101)
stem(final.exam,scale=2)