VALID CONFIDENCE INTERVALS FOR POST-MODEL-SELECTION PREDICTORS

被引:24
作者
Bachoc, Francois [1 ]
Leeb, Hannes [2 ,3 ]
Potscher, Benedikt M. [2 ]
机构
[1] Univ Paul Sabatier, Dept Math, F-31062 Toulouse, France
[2] Univ Vienna, Dept Stat, A-1090 Vienna, Austria
[3] DataSci Univie, Vienna, Austria
基金
奥地利科学基金会;
关键词
Inference post-model-selection; confidence intervals; optimal post-model-selection predictors; nonstandard targets; linear regression; VARIABLE SELECTION; INFERENCE; ESTIMATORS; LIKELIHOOD;
D O I
10.1214/18-AOS1721
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
We consider inference post-model-selection in linear regression. In this setting, Berk et al. [Ann. Statist. 41 (2013a) 802-837] recently introduced a class of confidence sets, the so-called PoSI intervals, that cover a certain nonstandard quantity of interest with a user-specified minimal coverage probability, irrespective of the model selection procedure that is being used. In this paper, we generalize the PoSI intervals to confidence intervals for post-model-selection predictors.
引用
收藏
页码:1475 / 1504
页数:30
相关论文
共 36 条