Cumulative logit models for ordinal data: a case study involving allergic rhinitis severity scores

Ordered categorical data arise in numerous settings, a common example being pain scores in analgesic trials. The modelling of such data is intrinsical ly more difficult than the modelling of continuous data due to the constrai nts on the underlying probabilities and the reduced amount of information t hat discrete outcomes contain. In this paper we discuss the class of cumula tive logit models, which provide a natural framework for ordinal data analy sis. We show how viewing the categorical outcome as the discretization of a n underlying continuous response allows a natural interpretation of model p arameters. We also show how covariates are incorporated into the model and how various types of correlation among repeated measures on the same indivi dual may be accounted for. The models are illustrated using longitudinal al lergy data consisting of sneezing scores measured on a four-point scale. Ou r approach throughout is Bayesian and we present a range of simple diagnost ics to aid model building. Copyright (C) 2001 John Wiley & Sons, Ltd.