Scholarlink

<p>This work examines explicitly the use of the Markov chain Monte Carlo (MCMC) approach to estimate the Kappa distribution’s parameters. OpenBUGS, a well-established program for Bayesian analysis using the MCMC approach, is used to calculate Bayesian estimations for the Kappa model’s parameters. The samples used to estimate Kappa parameters are presumed to be selected from a function of posterior density with independent set of priors that are not informative. A module was built and added to OpenBUGS to estimate the Bayes estimators of the Kappa distribution. OpenBUGS may be used to create statistically consistent parameter estimates and their corresponding credible intervals. Finally, a comparison is made between the maximum likelihood estimate and the Bayes estimates using some results and graphs. This study demonstrates that the computational MCMC approach can be easily implemented. A detailed methodology for using MCMC to estimate the Kappa distribution’s parameters is shown using survival data from patients with bladder cancer.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Kappa model for analyzing lifetime data with MCMC

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年4月7日

查看全文
  • Ali A. Al-Shomrani

摘要

This work examines explicitly the use of the Markov chain Monte Carlo (MCMC) approach to estimate the Kappa distribution’s parameters. OpenBUGS, a well-established program for Bayesian analysis using the MCMC approach, is used to calculate Bayesian estimations for the Kappa model’s parameters. The samples used to estimate Kappa parameters are presumed to be selected from a function of posterior density with independent set of priors that are not informative. A module was built and added to OpenBUGS to estimate the Bayes estimators of the Kappa distribution. OpenBUGS may be used to create statistically consistent parameter estimates and their corresponding credible intervals. Finally, a comparison is made between the maximum likelihood estimate and the Bayes estimates using some results and graphs. This study demonstrates that the computational MCMC approach can be easily implemented. A detailed methodology for using MCMC to estimate the Kappa distribution’s parameters is shown using survival data from patients with bladder cancer.