lassopack: Model selection and prediction with regularized regression in Stata

Achim Ahrens, Christian B. Hansen, Mark E. Schaffer

Research output: Contribution to journalArticle

11 Downloads (Pure)

Abstract

In this article, we introduce lassopack, a suite of programs for regularized regression in Stata. lassopack implements lasso, square-root lasso, elastic net, ridge regression, adaptive lasso, and postestimation ordinary least squares. The methods are suitable for the high-dimensional setting, where the number of predictors p may be large and possibly greater than the number of observations, n. We offer three approaches for selecting the penalization (“tuning”) parameters: information criteria (implemented in lasso2), K-fold cross-validation and h-step-ahead rolling cross-validation for cross-section, panel, and time-series data (cvlasso), and theory-driven (“rigorous” or plugin) penalization for the lasso and square-root lasso for cross-section and panel data (rlasso). We discuss the theoretical framework and practical considerations for each approach. We also present Monte Carlo results to compare the performances of the penalization approaches.

Original languageEnglish
Pages (from-to)176-235
Number of pages60
JournalStata Journal
Volume20
Issue number1
Early online date24 Mar 2020
DOIs
Publication statusPublished - Mar 2020

Keywords

  • cross-validation
  • cvlasso
  • cvlassologit
  • elastic net
  • lasso
  • lasso2
  • lasso2 postestimation
  • lassologit
  • lassologit postestimation
  • rlasso
  • rlasso postestimation
  • rlassologit
  • square-root lasso
  • st0594

ASJC Scopus subject areas

  • Mathematics (miscellaneous)

Fingerprint Dive into the research topics of 'lassopack: Model selection and prediction with regularized regression in Stata'. Together they form a unique fingerprint.

  • Cite this