Link William A, Albers Peter H
U.S. Geological Survey Patuxent Wildlife Research Center, Laurel, Maryland 20708, USA.
Environ Toxicol Chem. 2007 Sep;26(9):1867-72. doi: 10.1897/06-597R.1.
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.
分析人员假定暴露与反应之间关系的数学模型，估计模型参数，并根据该模型报告结论。此类分析很少考虑与模型选择相关的不确定性。贝叶斯推断系统为模型选择和多模型推断提供了一个便利的框架。在本文中，我们简要描述贝叶斯范式和贝叶斯多模型推断。然后，我们提出了一族用于多项剂量反应数据的模型，并将贝叶斯多模型推断方法应用于分析暴露于各种亚致死饮食浓度甲基汞的美洲红隼（Falco sparverius）繁殖成功率的数据。
