Exact conditional inference in models for longitudinal designs

Abstract This article discusses an exact inference approach in longitudinal experimental designs based on a discrete conditional distribution. It is derived from a mixed effects model for binary data (with logit link function) that is a generalization of the Rasch model. Exacthypothesis tests are suggested. Their application in scenarios of high practical relevance in empirical research is discussed. In a particular case, very common in clinical research, uniformly most powerful and uniformly most powerful unbiased tests are shown to exist. For computational reasons, the exact distributions are approximated by Monte Carlo techniques. All suggested procedures are illustrated in a hypothetical data example.