Statistical analysis for the doubly accelerated degradation Wiener model: An objective Bayesian approach

Abstract

Accelerated degradation test (ADT) provides an effective way to access the reliability of high-reliablity products. In this paper, a doubly accelerated degradation model based on the Wiener process is proposed to characterize the degradation path. An objective Bayesian approach is used to make inferences on the parameters of the model. Important objective priors including the Jeffreys prior and reference priors are derived for the parameters. It is shown that the corresponding posterior distributions are all proper, which implies that these priors enables posterior inferences. A simulation study is adopted to show the effectiveness of the proposed approach. Finally, the model is applied to analyze a real data set.