A Bayes approach to step-stress accelerated life testing

TLDR

Failure times at each stress level are exponentially distributed, but strict adherence to a time‑transformation function is not required. This paper develops a Bayesian model for step‑stress accelerated life testing. The authors construct a multivariate prior for failure rates across stress levels using prior information, and provide Bayes point estimates and probability statements for use‑stress life parameters. The prior preserves the natural ordering of failure rates in both prior and posterior estimates, and the method is illustrated with an example.

Abstract

This paper develops a Bayes model for step-stress accelerated life testing. The failure times at each stress level are exponentially distributed, but strict adherence to a time-transformation function is not required. Rather, prior information is used to define indirectly a multivariate prior distribution for the failure rates at the various stress levels. Our prior distribution preserves the natural ordering of the failure rates in both the prior and posterior estimates. Methods are developed for Bayes point estimates as well as for making probability statements for use-stress life parameters. The approach is illustrated with an example.