This document is intended to help describe how to undertake analyses introduced as examples in the Fourth Edition of (2014) by De Veaux, Velleman, and Bock. More information about the book can be found at http://wps.aw.com/aw_deveaux_stats_series. This file as well as the associated R Markdown reproducible analysis source file used to create it can be found at http://nhorton.people.amherst.edu/sdm4.
This work leverages initiatives undertaken by Project MOSAIC (http://www.mosaic-web.org), an NSF-funded effort to improve the teaching of statistics, calculus, science and computing in the undergraduate curriculum. In particular, we utilize the mosaic
package, which was written to simplify the use of R for introductory statistics courses. A short summary of the R needed to teach introductory statistics can be found in the mosaic package vignettes (http://cran.r-project.org/web/packages/mosaic).
Here we verify the calculations of expected counts for ballplayers by month (page 656).
ballplayer <- c(137, 121, 116, 121, 126, 114,
102, 165, 134, 115, 105, 122)
national <- c(0.08, 0.07, 0.08, 0.08, 0.08, 0.08,
0.09, 0.09, 0.09, 0.09, 0.08, 0.09)
n <- sum(~ ballplayer); n
## [1] 1478
sum(~ national)
## [1] 1
expect <- n*national
cbind(ballplayer, expect)
## ballplayer expect
## [1,] 137 118.24
## [2,] 121 103.46
## [3,] 116 118.24
## [4,] 121 118.24
## [5,] 126 118.24
## [6,] 114 118.24
## [7,] 102 133.02
## [8,] 165 133.02
## [9,] 134 133.02
## [10,] 115 133.02
## [11,] 105 118.24
## [12,] 122 133.02
The chi-square quantile values in the table on the bottom of page 658 can be verified using the xqt()
function.
xqchisq(c(.90, .95, .975, .99, .995), df=1)
## [1] 2.7055 3.8415 5.0239 6.6349 7.8794
These results match the first row: other values can be calculated by changing the df
argument.
The goodness of fit test on page 659 can be verified by calculating the chi-square statistic.
chisq <- sum((ballplayer-expect)^2/expect); chisq
## [1] 26.484
1-xpchisq(chisq, df=11)
## [1] 0.005494
Data from one university regarding the association between postgraduation activity and area of study is displayed in Table 24.1 (page 663).
area <- c(rep("agriculture", 209), rep("arts/science", 198),
rep("engineering", 177), rep("ILR", 101),
rep("agriculture", 104), rep("arts/science", 171),
rep("engineering", 158), rep("ILR", 33),
rep("agriculture", 135), rep("arts/science", 115),
rep("engineering", 39), rep("ILR", 16))
activity <- c(rep("Employed", 685), rep("Grad school", 466),
rep("Other", 305))
tally(~ activity + area, margins=TRUE)
## area
## activity agriculture arts/science engineering ILR Total
## Employed 209 198 177 101 685
## Grad school 104 171 158 33 466
## Other 135 115 39 16 305
## Total 448 484 374 150 1456
mosaicplot(tally(~ activity + area), main="mosaicplot of activity by area",
color=TRUE)
xchisq.test(tally(~ activity + area))
##
## Pearson's Chi-squared test
##
## data: x
## X-squared = 93.7, df = 6, p-value <2e-16
##
## 209 198 177 101
## (210.77) (227.71) (175.95) ( 70.57)
## [ 0.0149] [ 3.8754] [ 0.0062] [13.1215]
## <-0.122> <-1.969> < 0.079> < 3.622>
##
## 104 171 158 33
## (143.38) (154.91) (119.70) ( 48.01)
## [10.8181] [ 1.6720] [12.2543] [ 4.6918]
## <-3.289> < 1.293> < 3.501> <-2.166>
##
## 135 115 39 16
## ( 93.85) (101.39) ( 78.34) ( 31.42)
## [18.0470] [ 1.8277] [19.7590] [ 7.5689]
## < 4.248> < 1.352> <-4.445> <-2.751>
##
## key:
## observed
## (expected)
## [contribution to X-squared]
## <Pearson residual>
Note that the xchisq.test()
function displays the standardized residuals as the last item in each cell of the table (and these match the results in Table 24.4 (page 668).