Inference in randomized studies with informative censoring and discrete time-to-event endpoints

In this article. we present a method for estimating and comparing the treat ment-specific distributions of a discrete time-to-event variable from right -censored data. Our method allows for (1) adjustment for informative censor ing due to measured prognostic factors for time to event and censoring and (2) quantification of the sensitivity of the inference to residual dependen ce between time to event and censoring due to unmeasured factors. We develo p our approach in the context of a randomized trial for the treatment of ch ronic schizophrenia. We perform a simulation study to assess the practical performance of our methodology.