ABSTRACT
It is important to have a sample of the right size to allow a clinically relevant effect to be detected. Sample size calculations are therefore helpful and should always be done before carrying out a study. The power of a study is the probability of rejecting a false null hypothesis, so it is 1- ß. This can be expressed as either a percentage or a proportion. Statistical power is used in the calculation of sample size. As sample size increases, so does the ability to reject a false null hypothesis. Beta is often set at 20%, so the power (1-ß) is 80% or 0.8. It is essential that a study has adequate power, this is normally considered to be at least 80% or 0.8. This chapter concentrates on sample size calculations for two common situations- continuous data for two independent groups and categorical data for two independent groups.
