Bayesian Modeling of Time Trends in Component Reliability Data via Markov Chain Monte Carlo Simulation

Conference · Fri Jun 01 00:00:00 EDT 2007

OSTI ID:911890

Kelly, D L

Markov chain Monte Carlo (MCMC) techniques represent an extremely flexible and powerful approach to Bayesian modeling. This work illustrates the application of such techniques to time-dependent reliability of components with repair. The WinBUGS package is used to illustrate, via examples, how Bayesian techniques can be used for parametric statistical modeling of time-dependent component reliability. Additionally, the crucial, but often overlooked subject of model validation is discussed, and summary statistics for judging the model’s ability to replicate the observed data are developed, based on the posterior predictive distribution for the parameters of interest.

• Research Organization: Idaho National Lab. (INL), Idaho Falls, ID (United States)
• Sponsoring Organization: USDOE
• DOE Contract Number: DE-AC07-99ID-13727
• OSTI ID: 911890
• Report Number(s): INL/CON-06-11953; TRN: US200801%%340
• Resource Relation: Conference: 2007 ESREL Safety and Reliability Conference,University of Stavanger, Norway,06/25/2007,06/27/2007
• Country of Publication: United States
• Language: English

Related Subjects

99 - GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE
DISTRIBUTION
RELIABILITY
REPAIR
SAFETY
SIMULATION
STATISTICS
VALIDATION
Bayesian modeling
component reliability
Markov chain Monte Carlo (MCMC)
posterior predictive distribution