ABSTRACT
The sample size calculations presented in this book rely on the framework of statistical power analysis. Power analysis is closely related to the statistical tool of null hypothesis testing. A review of null hypothesis testing and power analysis is given in the following section, which is followed by Sections 3.2 and 3.3 in which the different types of power analysis and the timing of power analysis are discussed. In the ideal case, simple mathematical expressions for power analysis can be derived. Unfortunately, this is not always possible and one has to rely on other methods such as simulation studies, as discussed in Section 3.4. The different factors that influence a power analysis are topics of Section 3.5. Section 3.6 provides an overview of the steps that should be taken in a power analysis. One of these steps is the choice of an appropriate research design. Some general considerations with respect to the design of experiments are given in Section 3.7. Sections 3.8 and 3.9 focus on two alternative methods for sample size calculation: precision analysis and accuracy of parameter estimates.
