Date of Award

2015-01-01

Degree Name

Master of Science

Department

Mathematical Sciences

Advisor(s)

Naijun Sha

Abstract

A Bayesian analysis for the Weibull proportional hazard (PH) model is presented. A comparison between the Weibull PH model and the Weibull cumulative exposure (CE) model is made graphically and mathematically. The PH model is as flexible as the CE model in fitting step-stress data and the mathematical form of the PH model enables researchers to do Bayesian inferencemuch easier than the CE model. In addition, the PH model has the desirable proportional hazard property. A convex tent prior is used for Bayesian analysis. Markov chain Monte Carlo methods are used for posterior inferences. In this study, we adopt two sampling methods. The first way is to draw samples of the unknown parameters individually from each of the conditional posterior density functions. Another way is to perform joint sampling of the unknown parameters from the joint posterior density function. The performance of the two sampling methods is investigated using both simulated and real data sets.

Language

en

Provenance

Received from ProQuest

File Size

91 pages

File Format

application/pdf

Rights Holder

Hao Yang Teng

Share

COinS