Online Program Home
My Program

Abstract Details

Activity Number: 542
Type: Contributed
Date/Time: Wednesday, August 3, 2016 : 10:30 AM to 12:20 PM
Sponsor: Biometrics Section
Abstract #321406 View Presentation
Title: Semiparametric Spatial Model for Interval-Censored Data with Time-Varying Covariate Effect
Author(s): YUE ZHANG* and Xia Wang and Bin Zhang
Companies: University of Cincinnati and University of Cincinnati and Cincinnati Children's Hospital Medical Center
Keywords: Cox model ; Interval censoring ; Time-varying coefficient ; Spatial dependency ; Reversible jump MCMC ; Smoking cessation data

Cox regression model is the most commonly used method in the analysis of interval censored failure time data. In many practical studies, the covariate effects on the failure time may not be constant. Instead, they may vary over time. In recent studies, time-varying coefficients are of great interest due to their flexibility in capturing the temporal dynamic of covariate effects. In this article, we propose a Bayesian approach to dynamic Cox regression model allowing for spatial correlation with interval censored time-to-event data. With Bayesian approach, the coefficient curves are piecewise constant and the number of pieces and jump points are estimated from data. The posterior summaries are obtained via an efficient reversible jump Markov chain Monte Carlo algorithm. We illustrate our method by conducting simulation studies and our approach is shown to have better properties by comparing with several other existing methods. In addition, we apply our method to smoking cessation data in southeastern Minnesota. A conditional autoregressive distribution is employed to model the spatial dependency based on zip code identifiers for the subjects.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2016 program

Copyright © American Statistical Association