Joint Modeling Approach for Analyzing Complex Data with Latent Variables
The Chinese University of Hong Kong
This talk introduces several joint modeling approaches for analyzing complex data with latent variables. Several statistical models, including hidden Markov model, additive hazards model, transformation model, and regularized regression model, are considered to analyze multivariate longitudinal data, time-to-event data, and other non-normal data in the presence of latent variables. The estimating equation method, EM algorithm, and Bayesian methods are used to conduct statistical inference. Applications to real-life studies are presented.