Predictive specification of prior model probabilities in variable selection

• 成果类型: Article
• 署名作者: Laud, PW; Ibrahim, JG
• 署名单位: Harvard University; Harvard T.H. Chan School of Public Health
• 刊物名称: BIOMETRIKA
• ISSN/ISSBN: 0006-3444
• DOI: 10.1093/biomet/83.2.267
• 发表日期: 1996
• 页码: 267274
• 关键词: LINEAR-REGRESSION

摘要

We examine the problem of specifying prior probabilities for all possible subset models in the context of variable selection in normal linear models. A solution is proposed that uses a prior prediction for the observable, an associated weight, and prior opinion regarding error precision as the only required input. Numerical examples are given to illustrate the method.