ABSTRACT
Sample size is one of the most critical issues when designing a research study because the size of the sample affects all aspects of conducting the study and interpreting the results. Calculating sample size is a balancing act in which many factors need to be taken into account. For estimating sample size for studies designed to measure rare events, an upper limit of risk needs to be nominated, and then by substitution the sample size can be calculated. The sample sizes for calculating sensitivity and specificity are then added together to obtain the total sample size requirement. Internal pilot studies can be used to confirm sample size calculations. A priori sample size calculations underestimate the sample size required when the variance in the reference group is wider than expected. Ideally, the decision to stop any research study before the planned sample size is reached should be based on both statistical and ethical issues.
