Bayesian multimodel inference for dose-response studies

Environmental Toxicology and Chemistry
By:  and 



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 type Article
Publication Subtype Journal Article
Title Bayesian multimodel inference for dose-response studies
Series title Environmental Toxicology and Chemistry
DOI 10.1897/06-597R.1
Volume 26
Issue 9
Year Published 2007
Language English
Publisher Wiley
Contributing office(s) Patuxent Wildlife Research Center
Description 6 p.
First page 1867
Last page 1872
Google Analytic Metrics Metrics page
Additional publication details