A note on Bayesian prediction from the regression model with informative priors

被引:0
|
作者
Marriott, JM [1 ]
Spencer, NM [1 ]
机构
[1] Nottingham Trent Univ, Dept Math Stat & Operat Res, Nottingham NG1 4BU, England
关键词
Bayesian regression; informative priors; predictive densities;
D O I
10.1111/1467-842X.00195
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
This paper considers the problem of undertaking a predictive analysis from a regression model when proper conjugate priors are used. It shows how the prior information can be incorporated as a virtual experiment by augmenting the data, and it derives expressions for both the prior and the posterior predictive densities. The results obtained are of considerable practical importance to practitioners of Bayesian regression methods.
引用
收藏
页码:473 / 480
页数:8
相关论文
共 50 条