A0257
Title: A Bayesian quantile joint modeling of multivariate longitudinal and time-to-event data
Authors: Kiranmoy Das - Beijing Institute of Mathematical Sciences and Applications (China) [presenting]
Abstract: Linear mixed models are traditionally used for jointly modeling (multivariate) longitudinal outcomes and event-time(s). However, when the outcomes are non-Gaussian, a quantile regression model is more appropriate. In addition, in the presence of some time-varying covariates, it might be of interest to see how the effects of different covariates vary from one quantile level (of outcomes) to the other and, consequently, how the event-time changes across different quantiles. For such analyses, linear quantile mixed models can be used, and an efficient computational algorithm can be developed. A dataset from the acute lymphocytic leukemia (ALL) maintenance study conducted by Tata Medical Center, Kolkata is analyzed. For this dataset, a Bayesian quantile joint model is developed for the three longitudinal biomarkers and time-to-relapse. An asymmetric Laplace distribution (ALD) is considered for each outcome, and the mixture representation of the ALD is exploited to develop a Gibbs sampler algorithm to estimate the regression coefficients. The proposed model allows different quantile levels for different biomarkers, but still simultaneously estimates the regression coefficients corresponding to a particular quantile combination. Simulation studies are performed to assess the effectiveness of the proposed approach.
