and from
p¼
0 : 3 þ 0 : 5625
2
¼ 0 : 4313
a¼ 0 : 05 !z 1 a¼ 1 : 96 ðtwo-sided testÞ
b¼ 0 : 10 !z 1 b¼ 1 : 28
we obtain a required total sample size of
N¼ 4 ðz 1 aþz 1 bÞ^2
pð 1 pÞ
ðp 1 p 0 Þ^2
¼ð 4 Þð 1 : 96 þ 1 : 28 Þ^2
ð 0 : 4313 Þð 0 : 5687 Þ
ð 0 : 2625 Þ^2
F 146
or 73 cases and 73 controls are needed.
Example 12.15 Suppose that all specifications are the same as in Example
12.14, but we design a study in which the size of the control group is four times
the number of the cases. Here we have
p¼ð 0 : 3 Þð 0 : 8 Þþð 0 : 5625 Þð 0 : 2 Þ
¼ 0 : 3525
leading to a required total sample sizeN, satisfying
ffiffiffiffiffi
N
p
ð 0 : 5625 0 : 3 Þ¼ð 1 : 96 Þ
ffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffi
ð 0 : 3525 Þð 0 : 6475 Þð 5 þ 1 : 25 Þ
p
þð 1 : 28 Þ
ffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffi
ð 0 : 3 Þð 0 : 7 Þð 1 : 25 Þþð 0 : 5625 Þð 0 : 4375 Þð 5 Þ
p
NF 222
or 45 cases and 177 controls. It can be seen that the study requires a larger
number of subjects, 222 as compared to 146 subjects in Example 12.14; how-
ever, it may be easier to implement because it requires fewer cases, 45 to 73.
12.10.2 Matched Designs for a Binary Exposure
The design of a matched case–control study of a binary exposure is also speci-
fied by the very same two parameters: the exposure rate of the control groupp 0
and the relitive risk associated with the exposurey. The problem, however,
becomes more complicated because the analysis of a matched case–control
study of a binary exposure uses onlydiscordant pairs, pairs of subjects where
SAMPLE SIZE DETERMINATION FOR CASE–CONTROL STUDIES 471