MCMC in Estimation for Generalized Exponential Distribution with Constant Partially Accelerated Life Tests under Type-II Censoring Scheme

Abstract

Objective: Analysis of time-to-failure data, especially in a highly reliable product becomes very difficult due to small duration between production and release in the market. So, accelerated life testing (ALT) is the most widely used in the past few years in a product life testing. In this paper, we considered the lifetime generalized exponential distribution (GED) under constant stress partially ALT with Type-II censoring scheme. Material and Method: The maximum likelihood estimates (MLEs) of the parameters of GED and accelerate factor is present. The approximate confidence intervals (ACIs) based on the normal approximation to the asymptotic distribution of MLEs are constructed. Markov chain Monte Carlo (MCMC) for Bayesian point and interval estimation is tackled. Results: The measurement of developing methods is assessed and compared through numerical example and Monte Carlo simulation. Conclusion: Estimation results are more acceptable and Bayesian point and interval estimation are better than the approximate MLSs estimation.