COMPLIANCE IN AN ANTIHYPERTENSION TRIAL - A LATENT PROCESS MODEL FOR BINARY LONGITUDINAL DATA

We propose an alternative to the method of generalized estimating equa tions (GEE) for inference about binary longitudinal data. Unlike GEE, the method is practicable when the data consist of long time series on each subject and the set of observation times is not necessarily comm on to all subjects. Instead of modelling the intra-series correlations explicitly, we assume that a subject's propensity to respond is gover ned by an underlying, but unobserved, stationary continuous process. G iven a realization of this process, we assume that the binary response s are conditionally independent, with the probability that a subject r esponds positively at any given time t depending on the value of the u nderlying process at that time and also on any covariates specific to the subject at that time. We develop an algorithm for estimating the p arameters in this model, and investigate its effectiveness using simul ation methods. We also apply the methodology to data collected in a tr ial investigating the effect of self-measurement of blood pressure on compliance in taking medication during a course of anti-hypertension t reatment. (C) 1998 John Wiley & Sons, Ltd.