Unified LASSO estimation by least squares approximation

  • Wang H
  • Leng C
  • 84

    Readers

    Mendeley users who have this article in their library.
  • 145

    Citations

    Citations of this article.

Abstract

We propose a method of least squares approximation (LSA) for unified yet simple LASSO estimation. Our general theoretical framework includes ordinary least squares, generalized linear models, quantile regression, and many others as special cases. Specifically, LSA can transfer many different types of LASSO objective functions into their asymptotically equivalent least squares problems. Thereafter, the standard asymptotic theory can be established and the LARS algorithm can be applied. In particular, if the adaptive LASSO penalty and a Bayes information criterion–type tuning parameter selector are used, the resulting LSA estimator can be as efficient as the oracle. Extensive numerical studies confirm our theory.

Author-supplied keywords

  • Adaptive LASSO
  • Bayes information criterion
  • LASSO
  • Least angle regression
  • Least squares approximation
  • Microarray data
  • Oracle property
  • Solution path

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

Authors

  • Hansheng Wang

  • Chenlei Leng

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free