%0 Journal Article
%T An Integrated Procedure for Bayesian Reliability Inference Using MCMC
%A Jing Lin
%J Journal of Quality and Reliability Engineering
%D 2014
%R 10.1155/2014/264920
%X The recent proliferation of Markov chain Monte Carlo (MCMC) approaches has led to the use of the Bayesian inference in a wide variety of fields. To facilitate MCMC applications, this paper proposes an integrated procedure for Bayesian inference using MCMC methods, from a reliability perspective. The goal is to build a framework for related academic research and engineering applications to implement modern computational-based Bayesian approaches, especially for reliability inferences. The procedure developed here is a continuous improvement process with four stages (Plan, Do, Study, and Action) and 11 steps, including: (1) data preparation; (2) prior inspection and integration; (3) prior selection; (4) model selection; (5) posterior sampling; (6) MCMC convergence diagnostic; (7) Monte Carlo error diagnostic; (8) model improvement; (9) model comparison; (10) inference making; (11) data updating and inference improvement. The paper illustrates the proposed procedure using a case study. 1. Introduction The recent proliferation of Markov Chain Monte Carlo (MCMC) approaches has led to the use of the Bayesian inference in a wide variety of fields, including behavioural science, finance, human health, process control, ecological risk assessment, and risk assessment of engineered systems [1]. Discussions of MCMC-related methodologies and their applications in Bayesian Statistics now appear throughout the literature [2, 3]. For the most part, studies in reliability analysis focus on the following topics and their cross-applications: (1) hierarchical reliability models [4¨C7]; (2) complex system reliability analysis [8¨C10]; (3) faulty tree analysis [11, 12]; (4) accelerated failure models [13¨C17]; (5) reliability growth models [18, 19]; (6) masked system reliability [20]; (7) software reliability engineering [21, 22]; (8) reliability benchmark problems [23, 24]. However, most of the literature emphasizes the modelĄ¯s development; no studies offer a full framework to accommodate academic research and engineering applications seeking to implement modern computational-based Bayesian approaches, especially in the area of reliability. To fill the gap and to facilitate MCMC applications from a reliability perspective, this paper proposes an integrated procedure for the Bayesian inference. The remainder of the paper is organized as follows. Section 2 outlines the integrated procedure; this comprises a continuous improvement process including four stages and 11 sequential steps. Sections 3 to 8 discuss the procedure, focusing on (1) prior elicitation; (2) model
%U http://www.hindawi.com/journals/jqre/2014/264920/