UNIFORMLY VALID CONFIDENCE INTERVALS POST-MODEL-SELECTION

François Bachoc

doi:10.1214/19-AOS1815

UNIFORMLY VALID CONFIDENCE INTERVALS POST-MODEL-SELECTION

2020-02-01

25

OA

AI

DOI：10.1214/19-AOS1815

Original

Original request for help

Save

Abstract

En 中文

We suggest general methods to construct asymptotically uniformly valid confidence intervals post-model-selection. The constructions are based on principles recently proposed by Berk et al. (Ann. Statist. 41 (2013) 802-837). In particular, the candidate models used can be misspecified, the target of inference is model-specific, and coverage is guaranteed for any data-driven model selection procedure. After developing a general theory, we apply our methods to practically important situations where the candidate set of models, from which a working model is selected, consists of fixed design homoskedastic or heteroskedastic linear models, or of binary regression models with general link functions. In an extensive simulation study, we find that the proposed confidence intervals perform remarkably well, even when compared to existing methods that are tailored only for specific model selection procedures.

Keywords:

Inference post-model-selection

uniform asymptotic inference

regression

UNIFORMLY VALID CONFIDENCE INTERVALS POST-MODEL-SELECTION

Abstract

Journal

Organization