|
Activity Number:
|
166
- SPEED: Topics in Bayesian Analysis
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, July 30, 2018 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
|
Abstract #329794
|
|
|
Title:
|
A Bayesian Semiparametric Joint Model for Longitudinal and Survival Data
|
|
Author(s):
|
Pengpeng Wang* and Jonathan R. Bradley and Elizabeth H. Slate
|
|
Companies:
|
Florida State University and Florida State University and Florida State University
|
|
Keywords:
|
Joint Modeling;
Bayesian;
Semiparametric;
Longitudinal;
Survival;
Log-gamma
|
|
Abstract:
|
Many biomedical studies monitor both a longitudinal marker and a survival time on each subject under study. Modeling these two endpoints as joint responses has the potential to improve inference for both. We consider the approach of Brown and Ibrahim (2003, Biometrics) that proposes a Bayesian hierarchical semiparametric joint model. The model links the longitudinal and survival endpoints by incorporating the mean longitudinal trajectory as a predictor for the survival time. The usual parametric mixed effects model for the longitudinal trajectory is relaxed by using a Dirichlet process prior on the coefficients. A Cox proportional hazards model is then used for the survival time. The complicated joint likelihood increases the computational complexity. We develop a computationally efficient method by using a multivariate log-gamma distribution instead of normal distribution to model the data. We use Gibbs sampling combined with Neal's algorithm (2000, JCGS) and the Metropolis-Hastings method for inference. A simulation study illustrates the procedure.
|
Authors who are presenting talks have a * after their name.
