Premium
Bayesian multimodel inference for dose‐response studies
Author(s) -
Link William A.,
Albers Peter H.
Publication year - 2007
Publication title -
environmental toxicology and chemistry
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.1
H-Index - 171
eISSN - 1552-8618
pISSN - 0730-7268
DOI - 10.1897/06-597r.1
Subject(s) - bayesian inference , bayesian probability , inference , statistical inference , model selection , multinomial distribution , computer science , selection (genetic algorithm) , bayesian hierarchical modeling , machine learning , bayesian statistics , statistics , artificial intelligence , mathematics
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.