Joint Models for Incomplete Longitudinal Data and Time-to-Event Data

Clinical studies often collect longitudinal and time-to-event data for each subject. Joint modeling is a powerful methodology evaluating the association between these data. The existing models, however, have not sufficiently addressed problem of missing data, which are commonly encountered in studies. In this paper, we introduce novel joint model with shared random effects incomplete Our proposed consists three submodels: linear mixed Cox proportional hazard time-to-dropout from study. By simultaneously estimating parameters included submodels, biases estimators expected to decrease under two scenarios. We estimated by Bayesian approach, performance our method was evaluated through Monte Carlo simulation