ABSTRACT
Whenever an epidemiological study is being planned, the question always arises of how many subjects to include — that is, what sample size to use. This is clearly a vital question and would constitute a crucial part of any research proposal. Too large a sample means wasted resources; the result may be statistically significant but have no practical significance, as when a very small relative risk, say below 1.05, turns out to be statistically significant. Rarely will such a small increase in risk be biologically or medically important. This issue was discussed in Section 3.5.5. On the other hand, too small a sample leads to lack of precision in the results. This may render the entire study worthless: a result that would have medical significance has little chance of being found statistically significant when it is true. For instance, when Frieman
et al.
