A transitional model for longitudinal binary data subject to nonignorable missing data

Binary longitudinal data are often collected in clinical trials when intere st is on assessing the effect of a treatment over time. Our application is a recent study of opiate addiction that examined the effect of a new treatm ent on repeated urine tests to assess opiate use over an extended follow-up . Drug addiction is episodic, and a new treatment may affect various featur es of the opiate-use process such as the proportion of positive urine tests over follow-up and the time to the first occurrence of a positive test. Co mplications in this trial were the large amounts of dropout and intermitten t missing data and the large number of observations on each subject. We dev elop a transitional model for longitudinal binary data subject to nonignora ble missing data and propose an EM algorithm for parameter estimation. We u se the transitional model to derive summary measures of the opiate-use proc ess that can be compared across treatment groups to assess treatment effect . Through analyses and simulations, we show the importance of property acco unting for the missing data mechanism when assessing the treatment effect i n our example.