A survey of Bayesian predictive methods for model assessment, selection and comparison
A survey of Bayesian predictive methods for model assessment, selection and comparison
复制标题
DOI：
10.1214/12-ss102
复制
发表时间：
2012
影响因子：
3.3
通讯作者：
Aki Vehtari;Janne Ojanen
中科院分区：
文献类型：
--
作者：
Aki Vehtari;Janne Ojanen
到目前为止，在统计文献中存在几种用于模型评估的方法，这些方法自称是贝叶斯预测方法。然而，这些方法所基于的决策理论假设并不总是在最初的文章中明确阐述。本次调查的目的是对贝叶斯预测模型的评估和选择方法以及与之密切相关的方法进行统一的回顾。我们回顾了在这种情况下做出的各种假设，并讨论了不同方法之间的联系，重点是每种方法如何逼近使用贝叶斯模型预测未来数据的预期效用。
To date, several methods exist in the statistical literature for model assessment, which purport themselves specifically as Bayesian predic- tive methods. The decision theoretic assumptions on which these methods are based are not always clearly stated in the original articles, however. The aim of this survey is to provide a unified review of Bayesian predictive model assessment and selection methods, and of methods closely related to them. We review the various assumptions that are made in this context and discuss the connections between different approaches, with an emphasis on how each method approximates the expected utility of using a Bayesian model for the purpose of predicting future data.