A0228
Title: Bayesian analysis of multivariate longitudinal binary data
Authors: Kuo-Jung Lee - National Cheng Kung University (Taiwan) [presenting]
Abstract: A Bayesian multivariate probit linear mixed model is proposed to analyze multivariate longitudinal binary data. We estimate the effects of the covariates on the responses while accounting for three types of complex correlations present in the data. These include the correlations within separate responses over time, cross-correlations between different responses at different times, and correlations between different responses at each time point. The correlation matrix is estimated using hypersphere decomposition to meet the positive definiteness constraint. Simulations and real examples are used to demonstrate the proposed methods.
