Bayesian multimodel inference for dose-response studies

Authors

  • William A. Link,

    Corresponding author
    1. U.S. Geological Survey Patuxent Wildlife Research Center, Gabrielson Laboratory, 12100 Beech Forest Road, Laurel, Maryland 20708
    • U.S. Geological Survey Patuxent Wildlife Research Center, Gabrielson Laboratory, 12100 Beech Forest Road, Laurel, Maryland 20708
    Search for more papers by this author
  • Peter H. Albers

    1. U.S. Geological Survey Patuxent Wildlife Research Center, Beltsville Lab, % Beltsville Agricultural Research Center-East, Building 308, 10300 Baltimore Avenue, Beltsville, Maryland 20705
    Search for more papers by this author

Abstract

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.

Ancillary