Steady-state Gibbs sampler estimation for lung cancer data |
| |
Authors: | Martin X. Dunbar Robert Vogel Lili Yu |
| |
Affiliation: | 1. Abbott Laboratories, 100 Abbott Park Road, Abbott Park, IL 60064, USA;2. Jiann-Ping Hsu College of Public Health, Karl E. Peace Center for Biostatistics, Georgia Southern University, Statesboro, GA 30460, USA |
| |
Abstract: | This paper is based on the application of a Bayesian model to a clinical trial study to determine a more effective treatment to lower mortality rates and consequently to increase survival times among patients with lung cancer. In this study, Qian et al. [13 J. Qian, D.K. Stangl, and S. George, A Weibull model for survival data: Using prediction to decide when to stop a clinical trial, in Bayesian Biostatistics, D. Berry and D. Stangl, eds., Marcel Dekker, New York, 1996, pp. 187–205. [Google Scholar]] strived to determine if a Weibull survival model can be used to decide whether to stop a clinical trial. The traditional Gibbs sampler was used to estimate the model parameters. This paper proposes to use the independent steady-state Gibbs sampling (ISSGS) approach, introduced by Dunbar et al. [3 M. Dunbar, H.M. Samawi, R. Vogel, and L. Yu, A more efficient Gibbs sampler estimation using steady state simulation: Application to public health studies, J. Stat. Simul. Comput. 10.1080/00949655.2013.770857.[Taylor &; Francis Online] , [Google Scholar]], to improve the original Gibbs sampler in multidimensional problems. It is demonstrated that ISSGS provides accuracy with unbiased estimation and improves the performance and convergence of the Gibbs sampler in this application. |
| |
Keywords: | Bayesian model clinical trial Markov chain Monte Carlo methods Gibbs sampler dependent steady-state Gibbs sampling independent steady-state Gibbs sampler steady-state ranked simulated sampling |
|
|