tabulated separately for males and females in Table E6.20 (‘‘low’’ means
below the median). Test to investigate the relationship between the dis-
ease (two categories: cases and controls) and the diet (four categories:
low fat and high fiber, low fat and low fiber, high fat and high fiber, high
fat and low fiber). State clearly your null and alternative hypotheses and
choice of test size.TABLE E6.20
Males Females
Diet Cases Controls Cases Controls
Low fat, high fiber 27 38 23 39
Low fat, low fiber 64 78 82 81
High fat, high fiber 78 61 83 76
High fat, low fiber 36 28 35 276.21 A case–control study was conducted in Auckland, New Zealand to
investigate the e¤ects of alcohol consumption on both nonfatal myo-
cardial infarction and coronary death in the 24 hours after drinking,
among regular drinkers. Data are tabulated separately for men and
women in Table E6.21. For each group, men and women, and for each
type of event, myocardial infarction and coronary death, test to compare
cases versus controls. State, in each analysis, your null and alternative
hypotheses and choice of test size.
TABLE E6.21
Myocardial
Infarction Coronary Death
Drink in the
Last 24 Hours Controls Cases Controls Cases
Men No 197 142 135 103
Yes 201 136 159 69
Women No 144 41 89 12
Yes 122 19 76 46.22 Refer to the data in Exercise 6.21, but assume that gender (male/female)
may be a confounder but not an e¤ect modifier. For each type of event,
myocardial infarction and coronary death, use the Mantel–Haenszel
method to investigate the e¤ects of alcohol consumption. State, in each
analysis, your null and alternative hypotheses and choice of test size.
6.23 Since incidence rates of most cancers rise with age, this must always be
considered a confounder. Stratified data for an unmatched case–control
study are shown in Table E6.23. The disease was esophageal cancer
EXERCISES 241