Reliability Analysis for Accelerated Life-Test with Progressive Hybrid Censored Data Using Geometric Process

Abstract

This paper considers the Geometric Process implementation of the constant stress accelerated life test model based on the progressive Type-I hybrid censored data. By assuming that the life variables under increasing stress levels form a Geometric Process, the likelihood functions are derived and then reduced to a single nonlinear equation to be solved numerically to obtain the maximum likelihood estimates (MLEs) of the parameters. Two bootstrap confidence intervals are proposed. The point and interval estimations for the component's reliability are also obtained. Finally, the Monte-Carlo simulation study is carried out to illustrate the proposed procedures.