Demographic and Behavioral Modifiers of Arsenic Exposure Pathways: A Bayesian Hierarchical Analysis of NHEXAS Data

• Activity Number: 291
• Type: Contributed
• Date/Time: Tuesday, July 31, 2007 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistics and the Environment
• Author(s): Rajib Paul*+ and Catherine A. Calder and Peter F. Craigmile and Thomas Santner
• Companies: The Ohio State University and The Ohio State University and The Ohio State University and The Ohio State University
• Keywords: Biomarkers ; Censored data ; EPA Region 5 ; MCMC ; Missing data ; Subpopulation analysis

Abstract

We describe a Bayesian hierarchical model that explains subpopulation-specific pathways of exposure to arsenic from sources in the environment to excretion from the human body. Our model is fitted to data collected as part of the National Human Exposure Assessment Survey (NHEXAS). Using demographic information (e.g., gender, age), as well as surrogates for environmental exposure (e.g., usage of gas equipment, average number of minutes spent in an enclosed workshop), we identify subpopulation differences in exposure routes. Missing and censored data are handled systematically in the Bayesian framework, and inferences on model parameters are obtained using a Markov chain Monte Carlo (MCMC) algorithm.