BAYESIAN CONSTRAINED VARIABLE SELECTION

被引：1

作者：

Farcomeni, Alessio ^{[1
]}

机构：

[1] Univ Roma La Sapienza, I-00185 Rome, Italy

来源：

STATISTICA SINICA | 2010年 / 20卷 / 03期

关键词：

Constraints; Gibbs sampler; hierarchical models; variable selection; MODEL; REGRESSION; LASSO;

D O I：

暂无

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：

By building on the stochastic search approach (George and McCulloch (1993)) we propose a strategy for performing constrained variable selection. We discuss hierarchical and grouping constraints, and introduce anti-hierarchical constraints in which the inclusion of a variable forces another to be excluded from the model. We prove consistency results about models receiving maximal posterior probability, and about the median model (Barbieri and Berger (2004)), and discuss extensions to generalized linear models.

引用

页码：1043 / 1062

页数：20

共 35 条

[1] [Anonymous], 1996, Bayesian Statistics 5: Proceedings of the Fifth Valencia International Meeting
[2] [Anonymous], 1963, ANAL VARIANCE
[3] [Anonymous], 2006, Journal of the Royal Statistical Society, Series B
[4] [Anonymous], 2001, IMS LECT NOTES MONOG
[5] [Anonymous], 1996, BAYESIAN STAT
[6] ATKINSON AC, 1978, BIOMETRIKA, V65, P39, DOI 10.1093/biomet/65.1.39
[7] AUTIN F, 2004, MAXISET COMP PROCEDU
[8] Optimal predictive model selection
Barbieri, MM
Berger, JO
[J]. ANNALS OF STATISTICS, 2004, 32 (03) : 870 - 897
[9] LIMITING BEHAVIOR OF POSTERIOR DISTRIBUTIONS WHEN MODEL IS INCORRECT
BERK, RH
[J]. ANNALS OF MATHEMATICAL STATISTICS, 1966, 37 (01): : 51 - &
[10] Chipman H., 2001, IMS LECT NOTES MONOG, P67, DOI DOI 10.1214/LNMS/1215540964.655

← 1 2 3 4 →