MULTILEVEL MODELS FOR REPEATED MEASUREMENT DATA - APPLICATION TO QUALITY-OF-LIFE DATA IN CLINICAL-TRIALS

Quality of life data present considerable statistical challenges becau se of their longitudinal and multi-dimensional nature, and also becaus e the available data are often very unbalanced through missing values. Here we exemplify the potential of multi-level models, that is, hiera rchical random coefficient models, for such data. The discussion is de veloped in the context of analysing the quality of life data from a tr ial of palliative treatment in non-small-cell lung cancer. Not only do multi-level models provide a flexible modelling framework for the inv estigation of the underlying behaviour of response, for example, givin g simple estimates of treatment effects, but they also permit a descri ption of the differences between subjects and allow the analysis of mu lti-dimensional outcomes. The assumptions of Normality, homogeneity, a nd independence of the within- and between-subject variance components can be investigated and the models can be extended to provide explici t modelling of variance heterogeneity. It is concluded that multi-leve l models, for which software is now available, provide a natural and p owerful approach to the analysis of longitudinal data in general, and multi-dimensional quality of life data in particular.