Use R to re-draw Figs. 8-4 (4th ed p. 270, 3rd ed p. 258), 8-8 (4th ed p. 274, 3rd ed p. 262) and 10-4 (4th ed p. 375, 3rd ed p. 357) from the text. Are the figures in the text acceptably accurate?
How robust are t confidence intervals against non-normality? Generate 1000 samples of n = 4 observations from an exponential distribution with mean=10 and, for each, compute the 95% t confidence interval for the mean. Is the coverage close to the 95% level intended? How large must n be for the actual confidence level to be close enough to 95%?
Fourth Edition
8-24
8-33
8-45
9-5 to 9-9
9-15 to 9-19
9-33
9-39
9-53
9-66
9-72
10-16
10-17
10-31
10-41
10-50
Third Edition
8-23
8-26
8-38
9-2 to 9-5
9-8 to 9-11
9-24
9-33
9-46
10-20
10-21
10-37
10-55