DETERMINING THE APPROPRIATE SAMPLE SIZE
1.
Sample size for Estimating . If
is used as an
estimate of
, we can be (1-
) 100% confident that the error will not exceed a specified
amount e when the sample size is
n =
The formula is
applicable if we know s but we can use
the s from a preliminary sample that is n>30 for our estimate
of s. The e, ,
, and s should have same measurement unit.
2.
Sample size for estimating p. If is used as an estimate of p, then we can be (1-
) 100% confident that the error will not exceed a chosen e
when the sample size is
n =
Note that the e here
is a proportion.
3.
Where it is not useful to pre-determine aor an earlier estimate of
is not available, use the alternative rule: If
is used as an estimate of p, we can be at least (1-
) 100% confident that the error will not exceed a chosen e
when the sample size is
n =