|
Activity Number:
|
199
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Tuesday, August 5, 2003 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Bayesian Stat. Sciences
|
| Abstract - #300526 |
|
Title:
|
Estimating Joint Distributions of Contaminants in U.S. Community Water System Sources
|
|
Author(s):
|
John R. Lockwood*+
|
|
Companies:
|
Carnegie Mellon University
|
|
Address:
|
109 Eileen Dr., Pittsburgh, PA, 15227,
|
|
Keywords:
|
water quality regulation ; Markov chain Monte Carlo ; multivariate spatial data ; censoring
|
|
Abstract:
|
The current framework for U.S. Environmental Protection Agency regulation of water quality in community drinking water supplies produces sequential rules for either single contaminants or small groups of similar contaminants. Some water industry experts have advocated the development of a more holistic regulatory process in which rules are promulgated less frequently but for larger contaminant classes. Such a framework would necessitate the expansion of existing regulatory evaluation methods to account for joint occurrence distributions of multiple contaminants. This talk presents Bayesian hierarchical methods for estimating these distributions from sparse data collected over a large spatial scale. The methods have numerous features desirable for empirical exploration of multicontaminant regulations, including the simultaneous estimation of spatial heterogeneity in contaminant levels and covariations among contaminants, as well as proper accounting of censored concentrations. The value of the methods in refining inferences about critical regulatory quantities is demonstrated via a case study of seven substances.
|
