Skip to main content
U.S. flag

An official website of the United States government

Bayesian multimodel inference for dose-response studies

January 1, 2007

Statistical inference in dose-response studies is model-based: The analyst posits a mathematical model of the relation between exposure and response, estimates parameters of the model, and reports conclusions conditional on the model. Such analyses rarely include any accounting for the uncertainties associated with model selection. The Bayesian inferential system provides a convenient framework for model selection and multimodel inference. In this paper we briefly describe the Bayesian paradigm and Bayesian multimodel inference. We then present a family of models for multinomial dose-response data and apply Bayesian multimodel inferential methods to the analysis of data on the reproductive success of American kestrels (Falco sparveriuss) exposed to various sublethal dietary concentrations of methylmercury.

Publication Year 2007
Title Bayesian multimodel inference for dose-response studies
DOI 10.1897/06-597R.1
Authors W. A. Link, P.H. Albers
Publication Type Article
Publication Subtype Journal Article
Series Title Environmental Toxicology and Chemistry
Index ID 5224975
Record Source USGS Publications Warehouse
USGS Organization Patuxent Wildlife Research Center