openintro (version 1.7.1)

openintro-package: OpenIntro data sets and supplemental functions

Description

This package is a supplement to OpenIntro Statistics, which is a free textbook available at openintro.org (at-cost paperbacks are also available for under $10 on Amazon). The package contains data sets used in the textbook along with custom plotting functions for reproducing book figures. Note that many functions and examples include color transparency. Some plotting elements may not show up properly (or at all) in some Windows versions.

Details

Package:	openintro
Type:	Package
Version:	1.5.0
Date:	2013-10-28
License:	GPL-2 | GPL-3
LazyLoad:	yes

boxPlot, buildAxis, densityPlot, dotPlot, edaPlot, histPlot, normTail, cars, marioKart, possum, run10, satGPA, textbooks

Some colors include transparency, which means they will not be plotted in some operating systems (e.g. Windows). However, the plots may be viewed if they are written to a PDF or PNG file first. For a discussion of this topic, please see

http://yihui.name/en/2007/09/semi-transparent-colors-in-r-color-image-as-an-example/

Two new functions, myPDF and myPNG, were created in this package and may also be used to set up nice plotting files that allow for transparency.

Examples

# NOT RUN {
#===> boxPlot <===#
data(run10)
par(mfrow=1:2)
boxPlot(run10$time)
boxplot(run10$time)

#===> histPlot, example 1 <===#
data(run10)
par(mfrow=c(2,2))
histPlot(run10$time)
histPlot(run10$time[run10$gender=='M'], probability=TRUE, xlim=c(30, 180),
	ylim=c(0, 0.025), hollow=TRUE)
histPlot(run10$time[run10$gender=='F'], probability=TRUE, add=TRUE,
	hollow=TRUE, lty=3, border='red')
legend('topleft', col=c('black', 'red'), lty=2:3, legend=c('M','F'))
histPlot(run10$time, col=fadeColor('yellow', '33'), border='darkblue',
	probability=TRUE, breaks=30, lwd=3)
brks <- c(40, 50, 60, 65, 70, 75, 80, seq(82.5, 120, 2.5), 125,
	130, 135, 140, 150, 160, 180)
histPlot(run10$time, probability=TRUE, breaks=brks,
	col=fadeColor('darkgoldenrod4', '33'))

#===> histPlot, example 2 <===#
data(cars)
par(mfrow=c(1,1))
histPlot(cars$price[cars$type=='small'], probability=TRUE, hollow=TRUE,
	xlim=c(0,50))
histPlot(cars$price[cars$type=='midsize'], probability=TRUE, hollow=TRUE,
	add=TRUE, border='red', lty=3)
histPlot(cars$price[cars$type=='large'], probability=TRUE, hollow=TRUE,
	add=TRUE, border='blue', lty=4)
legend('topright', lty=2:4, col=c('black', 'red', 'blue'),
	legend=c('small', 'midsize', 'large'))

#===> densityPlot <===#
data(tips)
par(mfrow=c(1,1))
densityPlot(tips$tip, tips$day)
legend('topright', col=c('black','red'), lty=1:2,
	legend=c('Tuesday', 'Friday'))

#===> identifying reasons for outliers <===#
data(marioKart)
par(mfrow=c(1,1))
boxPlot(marioKart$totalPr, marioKart$cond, horiz=TRUE)
these <- which(marioKart$totalPr > 80)
# see the data collection criteria for
# why these observations do not belong.
lines(rep(marioKart$totalPr[these[1]], 2), c(2.4, 2))
text(marioKart$totalPr[these[1]], 2.4, marioKart$title[these[1]],
	pos=3, cex=0.5)
lines(rep(marioKart$totalPr[these[2]], 2), c(1.6, 2))
text(marioKart$totalPr[these[2]], 1.6, marioKart$title[these[2]],
	pos=1, cex=0.5)

#===> compare plotting methods <===#
data(cars)
par(mfrow=c(1,1))
histPlot(cars$price, ylim=c(0, 0.1), axes=FALSE, ylab='',
	probability=TRUE, xlab='price')
axis(1)
boxPlot(cars$price, width=0.03, horiz=TRUE, add=0.067, axes=FALSE)
dotPlot(cars$price, at=0.095, add=TRUE)
densityPlot(cars$price, add=TRUE)

#===> controlling the number of axis labels <===#
#     specify the number of labels
data(textbooks)
x <- textbooks$diff
par(mfrow=c(3,1))
histPlot(x, axes=FALSE)
buildAxis(1, x, n=4, nMin=4, nMax=4)
histPlot(x, axes=FALSE)
buildAxis(1, x, n=5, nMin=5, nMax=5)
histPlot(x, axes=FALSE)
# no decent axis is found for this data with exactly six labels
# no min or max specified, only a target number of labels:
buildAxis(1, x, n=6)

#===> creating normal plots with tails <===#
par(mfrow=c(2,3), mar=c(3,3,1,1), mgp=c(1.7, 0.7, 0))
normTail(L=-2)
normTail(U=1, xLab='symbol', cex.axis=0.7)
normTail(M=c(-2,-0.3), col='#22558833')
normTail(5, 13, L=-5, M=c(0,3), U=12, xAxisIncr=2)
normTail(102, 4, xlim=c(97,110), M=c(100,103))
normTail(-10.0, 5.192, M=c(-5,2), digits=1, xAxisIncr=2)

#===> Exploratory Data Analysis Plot <===#
data(mlbBat10)
#edaPlot(mlbBat10)
# }

Run the code above in your browser using DataCamp Workspace