Application of the Bayesian dynamic survival model in medicine
Authors:
- 15 December 2009
- journal article
- research article
- Published by Wiley in Statistics in Medicine
- Vol. 29 (3) , 347-360
Abstract
The Bayesian dynamic survival model (BDSM), a time-varying coefficient survival model from the Bayesian prospective, was proposed in early 1990s but has not been widely used or discussed. In this paper, we describe the model structure of the BDSM and introduce two estimation approaches for BDSMs: the Markov Chain Monte Carlo (MCMC) approach and the linear Bayesian (LB) method. The MCMC approach estimates model parameters through sampling and is computationally intensive. With the newly developed geoadditive survival models and software BayesX, the BDSM is available for general applications. The LB approach is easier in terms of computations but it requires the prespecification of some unknown smoothing parameters. In a simulation study, we use the LB approach to show the effects of smoothing parameters on the performance of the BDSM and propose an ad hoc method for identifying appropriate values for those parameters. We also demonstrate the performance of the MCMC approach compared with the LB approach and a penalized partial likelihood method available in software R packages. A gastric cancer trial is utilized to illustrate the application of the BDSM. Copyright © 2009 John Wiley & Sons, Ltd.Keywords
This publication has 26 references indexed in Scilit:
- Generating survival times to simulate Cox proportional hazards modelsStatistics in Medicine, 2005
- On the Cox Model With Time-Varying Regression CoefficientsJournal of the American Statistical Association, 2005
- Markov chain Monte Carlo for dynamic generalised linear modelsBiometrika, 1998
- Likelihood analysis of non-Gaussian measurement time seriesBiometrika, 1997
- Proportional hazards tests and diagnostics based on weighted residualsBiometrika, 1994
- Covariance structure of the Gibbs sampler with applications to the comparisons of estimators and augmentation schemesBiometrika, 1994
- Flexible Methods for Analyzing Survival Data Using Splines, with Applications to Breast Cancer PrognosisJournal of the American Statistical Association, 1992
- Improving survival in gastric cancer: Review of 5-year survival rates in English language publications from 1970British Journal of Surgery, 1992
- Dynamic Bayesian Models for Survival DataJournal of the Royal Statistical Society Series C: Applied Statistics, 1991
- Dynamic Generalized Linear Models and Bayesian ForecastingJournal of the American Statistical Association, 1985