Bayesian perspectives for epidemiological research. II. Regression analysis
Bayesian perspectives for epidemiological research. II. Regression analysis
复制标题
DOI：
10.1093/ije/dyl289
复制
发表时间：
2007-02-01
影响因子：
7.7
通讯作者：
Greenland, Sander
中科院分区：
文献类型：
--
作者：
Greenland, Sander
本文介绍了扩展的基本贝叶斯方法使用数据先验回归建模，包括层次（多层次）模型。这些方法提供了一种替代的简约为导向的方法的频率回归分析。特别是，他们取代任意的变量选择标准的先验分布，并通过这样做，促进现实使用的不精确，但重要的先验信息。它们还允许使用标准回归包进行贝叶斯分析;人们只需要能够向数据集添加变量和记录。因此，该方法便于使用贝叶斯解决方案的稀疏数据，多重比较，亚组分析和研究偏差的问题。由于这些解决方案有一个频率论解释为“收缩”（惩罚）估计，方法也可以被视为一种手段，实施收缩方法多参数问题。
This article describes extensions of the basic Bayesian methods using data priors to regression modelling, including hierarchical (multilevel) models. These methods provide an alternative to the parsimony-oriented approach of frequentist regression analysis. In particular, they replace arbitrary variable-selection criteria by prior distributions, and by doing so facilitate realistic use of imprecise but important prior information. They also allow Bayesian analyses to be conducted using standard regression packages; one need only be able to add variables and records to the data set. The methods thus facilitate the use of Bayesian solutions to problems of sparse data, multiple comparisons, subgroup analyses and study bias. Because these solutions have a frequentist interpretation as 'shrinkage' (penalized) estimators, the methods can also be viewed as a means of implementing shrinkage approaches to multiparameter problems.