skip to main content

Title: Bayesian Modeling of Population Variability -- Practical Guidance and Pitfalls

With the advent of easy-to-use open-source software for Markov chain Monte Carlo (MCMC) simulation, hierarchical Bayesian analysis is gaining in popularity. This paper presents practical guidance for hierarchical Bayes analysis of typical problems in probabilistic safety assessment (PSA). The guidance is related to choosing parameterizations that accelerate convergence of the MCMC sampling and to illustrating the potential sensitivity of the results to the functional form chosen for the first-stage prior. This latter issue has significant ramifications because the mean of the average population variability curve (PVC) from hierarchical Bayes (or the mean of the point estimate distribution from empirical Bayes) can be very sensitive to this choice in cases where variability is large. Numerical examples are provided to illustrate the issues discussed.
Authors:
;
Publication Date:
OSTI Identifier:
933190
Report Number(s):
INL/CON-08-14208
TRN: US200814%%266
DOE Contract Number:
DE-AC07-99ID-13727
Resource Type:
Conference
Resource Relation:
Conference: PSAM-9,Hong Kong,05/18/2008,05/23/2008
Research Org:
Idaho National Laboratory (INL)
Sponsoring Org:
USDOE
Country of Publication:
United States
Language:
English
Subject:
99 GENERAL AND MISCELLANEOUS; CHAINS; CONVERGENCE; DISTRIBUTION; FUNCTIONALS; PROBABILISTIC ESTIMATION; RISK ASSESSMENT; SAMPLING; SENSITIVITY; SIMULATION Bayesian inference; Hierarchical Bayes; Population Variability