Detail

Valid Confidence Intervals for Post-Model-Selection Predictors

Author(s)
Francois Bachoc, Hannes Leeb, Benedikt Pötscher
Abstract

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.

Organisation(s)
Department of Statistics and Operations Research, Research Network Data Science
Journal
Annals of Statistics
Volume
47
Pages
1475-1504
No. of pages
30
ISSN
0090-5364
DOI
https://doi.org/10.1214/18-AOS1721
Publication date
06-2019
Peer reviewed
Yes
Austrian Fields of Science 2012
502025 Econometrics, 101029 Mathematical statistics
Keywords
ASJC Scopus subject areas
Statistics and Probability, Statistics, Probability and Uncertainty
Portal url
https://ucrisportal.univie.ac.at/en/publications/valid-confidence-intervals-for-postmodelselection-predictors(61f184a1-8509-4d44-a4dc-5060ea796ac7).html