Multicarving for high-dimensional post-selection inference

TL;DR

This paper introduces the multicarve method, inspired by multisplitting, to enhance stability and replicability in high-dimensional post-selection inference for linear and generalized linear models.

Contribution

It extends data carving techniques with multicarve to improve stability, incorporates group inference, and applies to generalized linear models.

Findings

Multicarve improves stability over traditional data carving.

Method applicable to generalized linear models.

Enhanced group inference capabilities.

Abstract

We consider post-selection inference for high-dimensional (generalized) linear models. Data carving (Fithian et al., 2014) is a promising technique to perform this task. However, it suffers from the instability of the model selector and hence, may lead to poor replicability, especially in high-dimensional settings. We propose the multicarve method inspired by multisplitting to improve upon stability and replicability. Furthermore, we extend existing concepts to group inference and illustrate the applicability of the methodology also for generalized linear models.