ABSTRACT
In this chapter, we shall introduce the following three practical and important types of statistical analysis plans or statistical models that you frequently encounter in many randomized controlled trials:
♦ models for the treatment effect at each scheduled visit, ♦ models for the average treatment effect, and ♦ models for the treatment by linear time interaction, which are illustrated with real data from a randomized controlled trial called Respiratory Data. It should be noted that the problem of which model should be used in our trial largely depends on the purpose of the trial. Furthermore, to contrast the traditional ANCOVA-type analysis frequently used in the prepost design (1:1 design) where the baseline measurement is used as a covariate, we shall introduce
♦ANCOVA-type models adjusting for baseline measurement for the 1:T design. Finally, sample size calculations needed for some models with S:T repeated measures design are presented and illustrated with real data.
