Hierarchical Model Building, Fitting, and Checking: A Behind-the-Scenes Look at a Bayesian Analysis of Arsenic Exposure Pathways

• Activity Number: 147
• Type: Invited
• Date/Time: Monday, August 2, 2010 : 10:30 AM to 12:20 PM
• Sponsor: Section on Bayesian Statistical Science
• Author(s): Peter F. Craigmile*+ and Catherine Calder and Hongfei Li and Rajib Paul and Noel A. Cressie
• Companies: The Ohio State University and The Ohio State University and IBM T.J. Watson Research Center and Western Michigan University and The Ohio State University
• Keywords: National Human Exposure Assessment Survey (NHEXAS) ; Bayesian learning ; environmental health ; Markov chain Monte Carlo (MCMC) algorithm ; model validation ; Arizona

Abstract

We present a behind-the-scenes look at a Bayesian hierarchical analysis of pathways of exposure to arsenic using the Phase I National Human Exposure Assessment Survey carried out in Arizona. Our analysis combines individual-level personal exposure measurements (biomarker and environmental media) with amient water, soil, and air observations. We include details of our model-building exercise that involved a combination of exploratory data analysis and substantive knowledge in exposure science. Then we present our strategies for model fitting, which involved piecing together components of the hierarchical model in a systematic fashion to assess issues including parameter identifiability, Bayesian learning, model fit, and convergence diagnostics. We also discuss practical issues of data management and algorithm debugging, especially in the light of missing and censored data.