When statistical tests are
planned it is necessary to decide on the
sample size. If the sample size is too small
it will not be possible to estimate the
values of statistical parameters to the
required degree of accuracy and level of
If the sample size is too large then the
test may be too sensitive. The weakness
of many types of hypothesis test is that
the only way to adjust the sensitivity of
the test is by selecting the appropriate
sample size. Refer to practical
vs statistical significance.
Large sample sizes are also more expensive.
For specific methods refer to: