EcoSta 2019: Start Registration
View Submission - EcoSta2019
Title: Bayesian joint models for longitudinal binary and survival data using general random effects covariance matrix Authors:  Keunbaik Lee - Sungkyunkwan University (Korea, South) [presenting]
Abstract: Joint models are proposed to analyze longitudinal binary data with survival times data. Unlike the previous researches, random effects covariance matrix in our proposed joint models is assumed to be serially correlated and heterogeneous using modified Cholesky decomposition. The resulting parameters are estimated via linear/loglinear models, and the estimated random effects covariance matrix is positive-definite. The proposed methods are illustrated using real data.