Sheng Luo PhD
Assistant Professor, Division of Biostatistics, U of Texas School of Public Health will speak on...
Robust Bayesian Inference for Multivariate Longitudinal Data Using Normal/Independent Distributions
Abstract: Many randomized clinical trials collect multivariate longitudinal measurements in different scales, e.g. binary, ordinal, and continuous. Multilevel item response models are used to evaluate the global treatment effects across multiple outcomes while accounting for all sources of correlation. Continuous measurements are often assumed to be normally distributed. But the model inference is not robust when the normality assumption is violated due to heavy tails and outliers. In this article, we develop a Bayesian method for multilevel item response models replacing the normal distributions with symmetric heavy-tailed normal/independent (NI) distributions. The inference is conducted using a Bayesian framework via Markov Chain Monte Carlo simulation implemented in BUGS language. Our proposed method is evaluated by simulation studies and is applied to ELLDOPA study, a motivating clinical trial assessing the effect of Levodopa therapy on the Parkinson Disease progression rate.