A0921
Title: Joint models for longitudinal, survival and variance processes
Authors: Christiana Charalambous - University of Manchester (United Kingdom) [presenting]
Abstract: There is increasing evidence in the literature that within-subject variability of repeatedly measured biomarkers is informative of disease progression, with a potential impact on risk prediction for cardiovascular disease, kidney disease, and prostate cancer. Motivated by this, joint models are proposed for survival outcomes, as well as both the mean and variance of longitudinal outcomes (biomarkers). These models are linked via heterogeneous random effects sharing the same distribution, allowing us to capture the pairwise associations between the three outcomes through the random effects covariance matrix. The modified Cholesky decomposition is used to reparameterise the conditional covariance of the longitudinal response, and a Bayesian framework is used for estimation. The performance of the proposed approach is demonstrated via simulation and application to a real dataset.
