Double shrunken selection operator

Yuzbasi B., Arashi M.

COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION, vol.48, no.3, pp.666-674, 2019 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 48 Issue: 3
  • Publication Date: 2019
  • Doi Number: 10.1080/03610918.2017.1395040
  • Journal Name: COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.666-674
  • Keywords: Double shrinking, LASSO, Linear regression model, MSE, Prediction error, Stein-type shrinkage estimator, VARIABLE SELECTION, SHRINKAGE, REGRESSION, ESTIMATORS, LIKELIHOOD, LASSO, STEIN
  • Inonu University Affiliated: No

Abstract

The least absolute shrinkage and selection operator (LASSO) is a prominent estimator which selects significant (under some sense) features and kills insignificant ones. Indeed the LASSO shrinks features larger than a noise level to zero. In this article, we force LASSO to be shrunken more by proposing a Stein-type shrinkage estimator emanating from the LASSO, namely the Stein-type LASSO. The newly proposed estimator proposes good performance in risk sense numerically. Variants of this estimator have smaller relative MSE and prediction error, compared to the LASSO, in the analysis of prostate cancer dataset.