Kybernetika 58 no. 1, 25-42, 2022

Bayesian reference analysis for proportional hazards model of random censorship with Weibull distribution

Maria Ajmal, Muhammad Yameen Danish and Ayesha TahiraDOI: 10.14736/kyb-2022-1-0025

Abstract:

This article deals with the objective Bayesian analysis of random censorship model with informative censoring using Weibull distribution. The objective Bayesian analysis has a long history from Bayes and Laplace through Jeffreys and is reaching the level of sophistication gradually. The reference prior method of Bernardo is a nice attempt in this direction. The reference prior method is based on the Kullback-Leibler divergence between the prior and the corresponding posterior distribution and easy to implement when the information matrix exists in closed-form. We apply this method to Weibull random censorship model and compare it with Jeffreys and maximum likelihood methods. It is observed that the closed-form expressions for the Bayes estimators are not possible; we use importance sampling technique to obtain the approximate Bayes estimates. The behaviour of maximum likelihood and Bayes estimators is observed via extensive numerical simulation. The proposed methodology is used for the analysis of a real-life data for illustration and appropriateness of the model is tested by Henze goodness-of-fit test.

Keywords:

Jeffreys prior method, reference prior method, random censorship model, Kaplan-Meier survival estimate, Henze goodness-of-fit test

Classification:

62N01, 62N05, 62F10, 62F15

References:

  1. A. A. Abu-Taleb, M. M. Smadi and A. J. Alawneh: Bayes estimation of the lifetime parameters for the exponential distribution. J. Math. Stat. 3 (2007), 106-108.   DOI:10.3844/jmssp.2007.106.108
  2. M. Ajmal, M. Y. Danish and A. Tahira: Objective Bayesian analysis for Weibull distribution with application to random censorship model. J. Stat. Comp. Sim. 92 (2022), 43-59.   DOI:10.1080/00949655.2021.1931210
  3. J. O. Berger and J. M. Bernardo: Estimating a product of means: Bayesian analysis with reference priors. J. Am. Stat. Assoc. 84 (1989), 200-207.   DOI:10.1080/01621459.1989.10478756
  4. J. O. Berger and J. M. Bernardo: Ordered group reference priors with applications to a multinomial problem. Biometrika 79 (1992), 25-37.   DOI:10.1093/biomet/79.1.25
  5. J. M. Bernardo: Reference posterior distributions for Bayesian inference (with discussion). J. R. Stat. Soc. B 41 (1979), 113-147.   CrossRef
  6. J. M. Bernardo: Bayesian Reference Analysis. A postgraduate tutorial course, Universitat de Valencia, Spain 1998.   CrossRef
  7. M. Y. Danish and M. Aslam: Bayesian inference for the randomly censored Weibull distribution. J. Stat. Comp. Sim. 84 (2014), 215-230.   DOI:10.1080/00949655.2012.704516
  8. M. Y. Danish, I. A. Arshad and M. Aslam: Bayesian inference for the randomly censored Burr type XII distribution. J. Appl. Stat. 45 (2018), 270-283.   DOI:10.1080/02664763.2016.1275530
  9. T. R. Fleming and D. P. Harrington: Counting Processes and Survival Analysis. Wiley, New York 1990.   CrossRef
  10. R. Garg, M. Dube, K. Kumar and H. Krishna: On randomly censored generalized inverted exponential distribution. Am. J. Math. Manag. Sci. 35 (2016), 361-379.   DOI:10.1080/01966324.2016.1236711
  11. N. Henze: A quick omnibus test for the proportional hazards model of random censorship. Statistics 24 (1993), 253-263.   DOI:10.1080/02331888308802412
  12. M. Hollander and F. Proschan: Testing to determine the underlying distribution using randomly censored data. Biometrics 35 (1979), 393-401.   DOI:10.2307/2530342
  13. A. M. Hossain and W. J. Zimmer: Comparison of estimation methods for Weibull parameters: complete and censored samples. J. Stat. Comp. Sim. 73 (2003), 145-153.   DOI:10.1080/00949650215730
  14. A. Joarder, H. Krishna and D. Kundu: Inference on Weibull parameters with conventional type I censoring. Comp. Stat. Data. Anal. 55 (2011), 1-11.   DOI:10.1016/j.csda.2010.04.006
  15. R. Johnson, S. Kotz and N. Balakrishnan: Continuous Univariate Distribution. Second edition. Wiley, New York 1995.   CrossRef
  16. E. L. Kaplan and P. Meier: Nonparametric estimation from incomplete observations. J. Am. Stat. Assoc. 53 (1958), 457-481.   DOI:10.1080/01621459.1958.10501452
  17. S. C. Kochar and F. Proschan: Independence of time and cause of failure in the multiple dependent competing risks model. Statist. Sinica 1 (1991), 295-299.   DOI:10.1016/0278-4319(91)90062-M
  18. J. A. Koziol and S. B. Green: A Cramer-von Mises statistic for randomly censored data. Biometrika 63 (1976), 465-474.   DOI:10.1093/biomet/63.3.465
  19. H. Krishna, Vivekanand and K. Kumar: Estimation in Maxwell distribution with randomly censored data. J. Stat. Comp. Sim. 85 (2015), 3560-3578.   DOI:10.1080/00949655.2014.986483
  20. D. Kundu: Bayesian inference and life testing plan for Weibull distribution in presence of progressive censoring. Technometrics 50 (2008), 144-154.   DOI:10.1198/004017008000000217
  21. H. Rinne: The Weibull Distribution, A Handbook. CRC Press 2008.   CrossRef