Bayesian Estimation and Variable Selection for Reliability in Multicomponent Systems

• Activity Number: 29
• Type: Contributed
• Date/Time: Sunday, July 31, 2016 : 2:00 PM to 3:50 PM
• Sponsor: Quality and Productivity Section
• Author(s): Yiqing Tian* and Howard Bondell and Alyson Wilson
• Companies: North Carolina State University and North Carolina State University and North Carolina State University
• Keywords: Bayesian method ; Reliability system ; Variable selection ; Missing data

Abstract

We consider how to extend Bayesian variable selection to the identification of actively changing components in a system. Specifically, we extend the joint credible region approach (Bondell and Reich 2012) to the situation when we have pass/fail data on components, subsystems, and the full system and we want to assess system reliability. We consider two approaches to implementing the variable selection approach: one following Hamada et al. (2004) and the other where we treat component data as missing system data and impute the "missing" values.