ABSTRACT
The previous chapters focused on trials where the outcome variable was measured at one point in time post treatment. In this chapter an extension is made to trials where multiple measurements across time are taken, for instance, at pretest, at posttest and at one or more follow-up occasions. Such a trial is called a longitudinal intervention study and its data have a multilevel data structure with repeated measurements nested within subjects. As measurements within a given subject are likely to be correlated, the multilevel model is the appropriate model for data analysis. The next section gives a short introduction to the multilevel model for longitudinal data; for a more extensive introduction the reader is referred to Hedeker and Gibbons (2006) and Singer and Willett (2003).
