Bayesian analysis for hazard models with non-constant shape parameter

DOI10.1007/S001800100063MaRDI QIDQ1861607zbMATH OpenOpenAlexFDO

Authors Francisco Louzada

Publication date 9 March 2003

Published in Computational Statistics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s001800100063

zbMATH Keywords

accelerated lifetime testextended hazard regression modelLaplace methodWeibull model

Mathematics Subject Classification ID

Bayesian inference (62F15) Estimation in survival analysis and censored data (62N02) Reliability and life testing (62N05)

Review text

An extended regression model is described where the shape parameter is allowed to be dependent on covariates. As an example, the author considers the Weibull case \[ h(t |z_1,z_2)=e^{-\alpha^Tz_1}e^{\gamma^T z_2}\left[e^{-\alpha^Tz_1}t \right]^{\exp(\gamma^Tz_2)-1}, \] where \(z=(z_1,z_2)\) is the covariates vector. The Laplace method of integral approximation is used for the evaluation of the marginal posterior density of \(\alpha\) and \(\gamma\). Results of analysis of PET film data are presented.

Recommendations

• Extended hazard regression model for reliability and survival analysis
• scientific article; zbMATH DE number 1219013
• Bayesian modeling of bathtub shaped hazard rate using various Weibull extensions and related issues of model selection
• scientific article; zbMATH DE number 2138430
• Bayesian estimation of the Cox model under different hazard rate shape assumptions via slice sampling

Cited in

(5)

• Diagnostic analysis for heterogeneous log-Birnbaum-Saunders regression models
• scientific article; zbMATH DE number 2138430 (Why is no real title available?)
• Connections of Gini, Fisher, and Shannon by Bayes risk under proportional hazards
• scientific article; zbMATH DE number 5019640 (Why is no real title available?)
• Bayesian analysis for monotone hazard ratio

This page was built for publication: Bayesian analysis for hazard models with non-constant shape parameter

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1861607)