Discussion: "A significance test for the lasso"

TL;DR

This paper discusses the significance testing method for the lasso introduced by Lockhart et al., analyzing its statistical properties and implications for variable selection in high-dimensional models.

Contribution

It provides a critical discussion and interpretation of the significance test for the lasso, highlighting its advantages and limitations in statistical inference.

Findings

The significance test effectively identifies relevant variables.

The method controls false discovery rates in high-dimensional settings.

Insights into the test's applicability and robustness are provided.

Abstract

Discussion of "A significance test for the lasso" by Richard Lockhart, Jonathan Taylor, Ryan J. Tibshirani, Robert Tibshirani [arXiv:1301.7161].