English

A Comparison of Hamming Errors of Representative Variable Selection Methods

Statistics Theory 2022-03-30 v1 Statistics Theory

Abstract

Lasso is a celebrated method for variable selection in linear models, but it faces challenges when the variables are moderately or strongly correlated. This motivates alternative approaches such as using a non-convex penalty, adding a ridge regularization, or conducting a post-Lasso thresholding. In this paper, we compare Lasso with 5 other methods: Elastic net, SCAD, forward selection, thresholded Lasso, and forward backward selection. We measure their performances theoretically by the expected Hamming error, assuming that the regression coefficients are iid drawn from a two-point mixture and that the Gram matrix is block-wise diagonal. By deriving the rates of convergence of Hamming errors and the phase diagrams, we obtain useful conclusions about the pros and cons of different methods.

Keywords

Cite

@article{arxiv.2203.15075,
  title  = {A Comparison of Hamming Errors of Representative Variable Selection Methods},
  author = {Zheng Tracy Ke and Longlin Wang},
  journal= {arXiv preprint arXiv:2203.15075},
  year   = {2022}
}

Comments

87 pages; 13 figures

R2 v1 2026-06-24T10:29:02.603Z