Valid confidence intervals for post-model-selection predictors
Statistics Theory
2019-02-14 v3 Methodology
Statistics Theory
Abstract
We consider inference post-model-selection in linear regression. In this setting, Berk et al.(2013) recently introduced a class of confidence sets, the so-called PoSI intervals, that cover a certain non-standard 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 post-model-selection predictors.
Keywords
Cite
@article{arxiv.1412.4605,
title = {Valid confidence intervals for post-model-selection predictors},
author = {François Bachoc and Hannes Leeb and Benedikt M. Pötscher},
journal= {arXiv preprint arXiv:1412.4605},
year = {2019}
}
Comments
Some material added. Some restructuring of the paper. Some minor errors corrected