UTMB Health - The Office of Biostatistics
CTSA (Clinical & Translational Science Science Awards)
TRCC (Texas Regional CTSA Consortium) Quantitative Seminar Series
“Bayesian Models for Correlated Longitudinal Data from Multilevel Studies Involving Patients and Family Members”
Li-Jung Liang, Ph.D.
School of Medicine
Division of General Internal Medicine and Health Services Research
The University of California, Los Angeles
Tuesday, July 17, 2018 * Noon - 1 PM * Ewing Hall 1.104
This seminar contributes to achieving one or more of the CTSA core competencies in the category of Statistical Approaches.
Abstract: Correlated longitudinal data collected from multilevel studies that focus on the well-being of patients and their family members are generally complex. The important characteristics include multiple outcomes of interest collected longitudinally from multiple members within families and the interrelationships of these outcomes over time. A practical approach that can properly analyze such complex interconnected data is of interest. In this seminar, I will discuss Bayesian parametric and semi-parametric approaches that combine longitudinal regression with actor-partner interdependence models through shared random effects. The semi-parametric model uses a non-parametric prior, i.e., Dirichlet process prior, for the shared random effects to relax the parametric assumption. I will demonstrate these approaches using a pilot multilevel study.
*** Lunch Provided ***
Participating TRCC Institutions include: UTMB, UTHSC-Houston, UTHSC-San Antonio, and UT Southwestern