ABSTRACT
The sample size required to detect a difference between a test proportion,
p
,
and a standard proportion value,
p
, is calculated from
f f f− 2 (for > 2)
y C p p n x
y e m x
=
!
n z p p z p p
p p =
−( ) − −( ) −
1 1
where
z
is the two-tailed
z
-value from the standard normal curve for the desired level of significance and
z
is the lower one-tailed
z
-value selected for the power required (probability of rejecting the null hypothesis when it should be rejected).