DISTRIBUTION-FREE FITTING OF LOGIT-MODELS WITH RANDOM EFFECTS FOR REPEATED CATEGORICAL RESPONSES

This article discusses random effects models for within-subject compar isons of repeated responses on the same categorical scale. The models account for the correlation that normally occurs between repeated resp onses. The standard way of fitting such models maximizes the marginal likelihood after integrating with respect to a distribution for the ra ndom effect. An alternative non-parametric approach does not assume a distributional form for the random effects. Recent literature shows th at for certain simple logit models, this approach yields essentially t he same model parameter estimates as conditional maximum likelihood. M oreover, these estimates also result from fitting corresponding quasi- symmetric log-linear models. For simple data sets in which primary int erest relates to subject-specific comparisons of the repeated response s, one can easily obtain the estimates with standard software for log- linear models. Examples include data from crossover designs and from c omparisons of treatment and control groups regarding the change betwee n baseline and follow-up observations.