meanSEC <- mean(SDS4$times)
meanMIN <- mean(SDS4$times/60)
c(meanSEC, meanMIN)[1] 7.80 0.13sdSEC <- sd(SDS4$times)
sdMIN <- sd(SDS4$times/60)
c(sdSEC, sdMIN)[1] 7.871402 0.131190CVsec <- meanSEC/sdSEC
CVmin <- meanMIN/sdMIN
c(CVsec, CVmin)[1] 0.9909289 0.9909289The code defining the CV has \(\bar{X}/S\) instead of \(S/\bar{X}\). The code should be changed as shown below.
meanSEC <- mean(SDS4$times)
meanMIN <- mean(SDS4$times/60)
c(meanSEC, meanMIN)[1] 7.80 0.13sdSEC <- sd(SDS4$times)
sdMIN <- sd(SDS4$times/60)
c(sdSEC, sdMIN)[1] 7.871402 0.131190CVsec <- sdSEC/meanSEC
CVmin <- sdMIN/meanMIN
c(CVsec, CVmin)[1] 1.009154 1.009154Page 209: …conditioning event G, then enumerating… should read: conditioning event G, than enumerating
Page 244: Problem 54 - Given the following cumulative density function should read Given the following cumulative distribution function
Page 340: R Code 5.15 - facet_grid(. ~ r) should
read facet_grid(. ~ r, labeller = label_parsed)
Page 381: The solution for Example 6.16 has \(P \dot\sim N\left(0.383, \sqrt{\tfrac{(0.383)(0.617)}{250}} = 0.0019 \right).\) The solution should read:
\[P \dot\sim N\left(0.383, \sqrt{\tfrac{(0.383)(0.617)}{250}} = 0.0307 \right)\]
Page 485: lep <- (15 - 1) + 5.2449/uchi should be
lep <- (15 - 1) + 5.2429/uchi, and
uep <- (15 - 1) + 5.2449/lchi should be
uep <- (15 - 1) + 5.2429/lchi
Page 497 leads to the quadratic equation \(\left(z_{1-\alpha/2}^2 + n \right)p^2 -\left( 2n\hat{p} + z_{1-\alpha/2} \right)p + n\hat{p}^2\) should be \(\left(z_{1-\alpha/2}^2 + n \right)p^2 -\left( 2n\hat{p} + z_{1-\alpha/2}^2 \right)p + n\hat{p}^2\)
Page 545: Exampe 9.11 - STCHOOL should be
STSCHOOL
Page 551: \(T=\frac{\bar{D}-\mu_{D}}{S_D/\sqrt{n_D}} \sim t_{n - 1}\) should be \(T=\frac{\bar{D}-\mu_{D}}{S_D/\sqrt{n_D}} \sim t_{n_D - 1}\)
With update in ggplot2, everywhere
ggplot_hline(y = value) appears now needs to be
ggplot_hline(yintercept = value)
Page 717 problem (e) has
\[\begin{align*} \lambda &= \dfrac{SS_{Hypothesis}}{\sigma^2}\\ &=\frac{\sum_{i=1}^a n_i (\mu_{i\bullet} - \bar{\mu}_{\bullet\bullet})^2}{\sigma^2} \\ &= \dfrac{ 6\cdot(390-405)^2 + 6\cdot(405-405)^2 + 12\cdot(415-405)^2 + 12\cdot(410-405)^2}{14^2} \\ &= \dfrac{2635}{14^2} = 13.3929. \end{align*}\]
In the case with uneven sample sizes, \(\bar{\mu}_{\bullet\bullet} = \frac{(6\cdot390 + 6\cdot405 + 12 \cdot 415 + 12 \cdot 410)}{(6 + 6 + 12 + 12)}= 407.5\), and the 405 should be replaced with 407.5 as shown below.
\[\begin{align*} \lambda &= \dfrac{SS_{Hypothesis}}{\sigma^2}\\ &=\frac{\sum_{i=1}^a n_i (\mu_{i\bullet} - \bar{\mu}_{\bullet\bullet})^2}{\sigma^2} \\ &= \dfrac{ 6\cdot(390-407.5)^2 + 6\cdot(405-407.5)^2 + 12\cdot(415-407.5)^2 + 12\cdot(410-407.5)^2}{14^2} \\ &= \dfrac{2635}{14^2} = 13.3929. \end{align*}\]