Role of detection limits in drinking water regulation.

Some commentators on environmental science and policy have claimed that advances in analytical chemistry, reflected by an ability to detect contaminants at ever-decreasing concentrations, lead to regulations stricter than justified by available toxicological data. We evaluate this claim in the context of drinking water regulation, with respect to contaminants regulated under the Safe Drinking Water Act (SDWA). We examine the relationships between historical and present maximum contaminant levels and goals in the greater context of detection capability and evaluate the extent to which different aspects of the regulatory apparatus (i.e., analytical capability, cost-benefit analysis, analysis of competing risks, and available toxicological data) influence the regulatory process. Our findings do not support the claim that decreases in detection limit lead to more stringent regulation in the context of drinking water regulation in the United States. Further, based on our analysis of the National Primary Drinking Water Regulation and existing United States Environmental Protection Agency approaches to establishing the practical quantifiable level, we conclude that in the absence of changes to the underlying toxicological model, regulatory revision is unlikely.

A Bayesian approach to a logistic regression model with incomplete information.

We consider a set of independent Bernoulli trials with possibly different success probabilities that depend on covariate values. However, the available data consist only of aggregate numbers of successes among subsets of the trials along with all of the covariate values. We still wish to estimate the parameters of a modeled relationship between the covariates and the success probabilities, e.g., a logistic regression model. In this article, estimation of the parameters is made from a Bayesian perspective by using a Markov chain Monte Carlo algorithm based only on the available data. The proposed methodology is applied to both simulation studies and real data from a dose-response study of a toxic chemical, perchlorate.