Assessing convergence diagnostic tests for Bayesian Cox regression


Alkan N.

COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION, vol.46, no.4, pp.3201-3212, 2017 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 46 Issue: 4
  • Publication Date: 2017
  • Doi Number: 10.1080/03610918.2015.1080835
  • Journal Name: COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.3201-3212
  • Keywords: Bayesian Cox regression, Convergence diagnostic tests, Markov Chain Monte Carlo, MONTE-CARLO CONVERGENCE, RUN LENGTH CONTROL, OUTPUT
  • Akdeniz University Affiliated: No

Abstract

The Markov chain Monte Carlo (MCMC) method generates samples from the posterior distribution and uses these samples to approximate expectations of quantities of interest. For the process, researchers have to decide whether the Markov chain has reached the desired posterior distribution. Using convergence diagnostic tests are very important to decide whether the Markov chain has reached the target distribution. Our interest in this study was to compare the performances of convergence diagnostic tests for all parameters of Bayesian Cox regression model with different number of iterations by using a simulation and a real lung cancer dataset.