ANALYSIS OF LONGITUDINAL BINARY DATA FROM MULTIPHASE SAMPLING

The efficient use of surrogate or auxiliary information has been inves tigated within both model-based and design-based approaches to data an alysis, particularly in the context of missing data. Here we consider the use of such data in epidemiological studies of disease incidence i n which surrogate measures of disease status are available for all sub jects at two time points, but definitive diagnoses are available only in stratified subsamples. We briefly review methods for the analysis o f two-phase studies of disease prevalence at a single time point, and we discuss the extension of four of these methods to the analysis of i ncidence studies. Their performance is compared with special reference to a study of the incidence of senile dementia.