On overfitting and post-selection uncertainty assessments

被引：17

作者：

Hong, L. ^{[1
]}

Kuffner, T. A. ^{[2
]}

Martin, R. ^{[3
]}

机构：

[1] Robert Morris Univ, Dept Math, 6001 Univ Blvd, Moon Township, PA 15108 USA

[2] Washington Univ, Dept Math, 1 Brookings Dr,Campus Box 1146, St Louis, MO 63130 USA

[3] North Carolina State Univ, Dept Stat, 2311 Stinson Dr,Campus Box 8203, Raleigh, NC 27695 USA

来源：

BIOMETRIKA | 2018年 / 105卷 / 01期

基金：

美国国家科学基金会;

关键词：

Akaike information criterion; Bayesian information criterion; Model selection; Regression; MODEL;

D O I：

10.1093/biomet/asx083

中图分类号：

Q [生物科学];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

In a regression context, when the relevant subset of explanatory variables is uncertain, it is common to use a data-driven model selection procedure. Classical linear model theory, applied naively to the selected submodel, may not be valid because it ignores the selected submodel's dependence on the data. We provide an explanation of this phenomenon, in terms of overfitting, for a class of model selection criteria.

引用

页码：221 / 224

页数：4

共 50 条

[1] Post-Selection Inference
Kuchibhotla, Arun K.
Kolassa, John E.
Kuffner, Todd A.
ANNUAL REVIEW OF STATISTICS AND ITS APPLICATION, 2022, 9 : 505 - 527
[2] Post-selection and quantum energetics
Rogers, Spencer
Jordan, Andrew N.
arXiv, 2022,
[3] VALID POST-SELECTION INFERENCE
Berk, Richard
Brown, Lawrence
Buja, Andreas
Zhang, Kai
Zhao, Linda
ANNALS OF STATISTICS, 2013, 41 (02): : 802 - 837
[4] The Limits of Post-Selection Generalization
Nissim, Kobbi
Smith, Adam
Steinke, Thomas
Stemmer, Uri
Ullman, Jonathan
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
[5] The post-selection operator current
Gray, John E.
Addison, Stephen R.
QUANTUM STUDIES-MATHEMATICS AND FOUNDATIONS, 2018, 5 (03) : 399 - 412
[6] An Analysis of Post-selection in Automatic Configuration
Yuan, Zhi
Stuetzle, Thomas
de Oca, Marco A. Montes
Lau, Hoong Chuin
Birattari, Mauro
GECCO'13: PROCEEDINGS OF THE 2013 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, 2013, : 1557 - 1564
[7] Automatic post-selection by ancillae thermalization
Wright, L.
Barratt, F.
Dborin, J.
Booth, G. H.
Green, A. G.
PHYSICAL REVIEW RESEARCH, 2021, 3 (03):
[8] Splitting strategies for post-selection inference
Rasines, D. Garcia
Young, G. A.
BIOMETRIKA, 2023, 110 (03) : 597 - 614
[9] On Post-selection Inference in A/B Testing
Deng, Alex
Li, Yicheng
Lu, Jiannan
Ramamurthy, Vivek
KDD '21: PROCEEDINGS OF THE 27TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2021, : 2743 - 2752
[10] The Post-Selection Probability Current and Its Implications
Gray, John E.
Parks, Allen D.
QUANTUM INFORMATION AND COMPUTATION VII, 2009, 7342

← 1 2 3 4 5 →