Statistical inference for the Arrhenius-Weibull accelerated life testing model with imprecision based on the likelihood ratio test

Abstract

In this article, we present a new imprecise statistical inference method for accelerated life testing data, where nonparametric predictive inferences at normal stress levels are integrated with a parametric Arrhenius-Weibull model. The method includes imprecision based on the likelihood ratio test which provides robustness with regard to the model assumptions. We use the likelihood ratio test to obtain an interval for the parameter of the Arrhenius link function providing imprecision into the method. The imprecision leads to observations at increased stress levels being transformed into interval-valued observations at the normal stress level, where the width of an interval is larger for observations from higher stress levels. If the model fits well, our method has relatively little imprecision. However, if the model fits poorly, it leads to more imprecision. Simulation studies are presented to investigate the performance of the proposed method.