Bayesian analysis for step-stress accelerated life testing using weibull proportional hazard model

Naijun Sha, Rong Pan

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

In this paper, we present a Bayesian analysis for the Weibull proportional hazard (PH) model used in step-stress accelerated life testings. The key mathematical and graphical difference between the Weibull cumulative exposure (CE) model and the PH model is illustrated. Compared with the CE model, the PH model provides more flexibility in fitting step-stress testing data and has the attractive mathematical properties of being desirable in the Bayesian framework. A Markov chain Monte Carlo algorithm with adaptive rejection sampling technique is used for posterior inference. We demonstrate the performance of this method on both simulated and real datasets.

Original languageEnglish (US)
Pages (from-to)715-726
Number of pages12
JournalStatistical Papers
Volume55
Issue number3
DOIs
StatePublished - 2014

Fingerprint

Accelerated Life Testing
Proportional Hazards Model
Weibull
Bayesian Analysis
Rejection Sampling
Adaptive Sampling
Markov Chain Monte Carlo Algorithms
Flexibility
Testing
Model
Demonstrate
Bayesian analysis
Proportional hazards model
Life stress

Keywords

  • Bayesian inference
  • Cumulative exposure model
  • Proportional hazard model
  • Step-stress accelerated life test
  • Weibull distribution

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Bayesian analysis for step-stress accelerated life testing using weibull proportional hazard model. / Sha, Naijun; Pan, Rong.

In: Statistical Papers, Vol. 55, No. 3, 2014, p. 715-726.

Research output: Contribution to journalArticle

@article{c464bf0bc53e434b9f3c8c38ead9fdf3,
title = "Bayesian analysis for step-stress accelerated life testing using weibull proportional hazard model",
abstract = "In this paper, we present a Bayesian analysis for the Weibull proportional hazard (PH) model used in step-stress accelerated life testings. The key mathematical and graphical difference between the Weibull cumulative exposure (CE) model and the PH model is illustrated. Compared with the CE model, the PH model provides more flexibility in fitting step-stress testing data and has the attractive mathematical properties of being desirable in the Bayesian framework. A Markov chain Monte Carlo algorithm with adaptive rejection sampling technique is used for posterior inference. We demonstrate the performance of this method on both simulated and real datasets.",
keywords = "Bayesian inference, Cumulative exposure model, Proportional hazard model, Step-stress accelerated life test, Weibull distribution",
author = "Naijun Sha and Rong Pan",
year = "2014",
doi = "10.1007/s00362-013-0521-2",
language = "English (US)",
volume = "55",
pages = "715--726",
journal = "Statistical Papers",
issn = "0932-5026",
publisher = "Springer New York",
number = "3",

}

TY - JOUR

T1 - Bayesian analysis for step-stress accelerated life testing using weibull proportional hazard model

AU - Sha, Naijun

AU - Pan, Rong

PY - 2014

Y1 - 2014

N2 - In this paper, we present a Bayesian analysis for the Weibull proportional hazard (PH) model used in step-stress accelerated life testings. The key mathematical and graphical difference between the Weibull cumulative exposure (CE) model and the PH model is illustrated. Compared with the CE model, the PH model provides more flexibility in fitting step-stress testing data and has the attractive mathematical properties of being desirable in the Bayesian framework. A Markov chain Monte Carlo algorithm with adaptive rejection sampling technique is used for posterior inference. We demonstrate the performance of this method on both simulated and real datasets.

AB - In this paper, we present a Bayesian analysis for the Weibull proportional hazard (PH) model used in step-stress accelerated life testings. The key mathematical and graphical difference between the Weibull cumulative exposure (CE) model and the PH model is illustrated. Compared with the CE model, the PH model provides more flexibility in fitting step-stress testing data and has the attractive mathematical properties of being desirable in the Bayesian framework. A Markov chain Monte Carlo algorithm with adaptive rejection sampling technique is used for posterior inference. We demonstrate the performance of this method on both simulated and real datasets.

KW - Bayesian inference

KW - Cumulative exposure model

KW - Proportional hazard model

KW - Step-stress accelerated life test

KW - Weibull distribution

UR - http://www.scopus.com/inward/record.url?scp=84903904425&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903904425&partnerID=8YFLogxK

U2 - 10.1007/s00362-013-0521-2

DO - 10.1007/s00362-013-0521-2

M3 - Article

AN - SCOPUS:84903904425

VL - 55

SP - 715

EP - 726

JO - Statistical Papers

JF - Statistical Papers

SN - 0932-5026

IS - 3

ER -