the total sample sizeNis given by
N¼
1
ðlnyÞ^2
1
w 1
þ
1
w 0
ðz 1 aþz 1 bÞ^2
For example, if we want the size of the control group to be three times the
number of the cases,w 1 ¼ 0 :25 andw 0 ¼ 0 :75.
Example 12.17 Suppose that an investigator is considering designing a case–
control study of a potential association between coronary heart disease and
serum cholesterol level. Suppose further that it is desirable to detect an odds
ratio ofy¼ 2 :0 for a person with a cholesterol level 1 standard deviation above
the mean for his or her age group using a two-sided test with a significance level
of 5% and a power of 90%. From
a¼ 0 : 05 !z 1 a¼ 1 : 96 ðtwo-sided testÞ
b¼ 0 : 10 !z 1 b¼ 1 : 28
the required total sample size is:
N¼
4
y^2
ðz 1 aþz 1 bÞ^2
¼
4
ðln 2Þ^2
ð 1 : 96 þ 1 : 28 Þ^2
F 62
if we plan a balanced study with each group consisting of 31 subjects.
Example 12.18 Suppose that all specifications are the same as in Example
12.17 but we design a study in which the size of the control group is three times
the number of cases. Here we have
N¼
1
½lnðyÞ^2
1
w 1
þ
1
w 0
ðz 1 aþz 1 bÞ^2
¼
1
½lnð 2 Þ^2
1
0 : 25
þ
1
0 : 75
ð 1 : 96 þ 1 : 28 Þ^2
F 84
or 21 cases and 63 controls.
SAMPLE SIZE DETERMINATION FOR CASE–CONTROL STUDIES 475