Skip to main content

Multivariate variable selection by means of null-beamforming

Zhang, Jian, Oftadeh, Elaheh (2021) Multivariate variable selection by means of null-beamforming. Electronic Journal of Statistics, 15 (1). pp. 3428-3477. ISSN 1935-7524. (doi:10.1214/21-EJS1859) (KAR id:96311)

PDF Publisher pdf
Language: English

Download (1MB)
[thumbnail of 21-EJS1859.pdf]
This file may not be suitable for users of assistive technology.
Request an accessible format
Official URL:


This article aims to use beamforming, a covariate-assisted data projection method to solve the problem of variable selection for multivariate random-effects regression models. The new approach attempts to explore the covariance structure in the data with a small number of random-effects covariates. The basic premise behind the proposal is to scan through a covariate space with a series of forward filters named null-beamformers; each is tailored to a particular covariate in the space and resistant to interference effects originating from other covariates. Applying the proposed method to simulated and real multivariate regression data, we show that it can substantially outperform the existing methods of multivariate variable selection in terms of sensitivity and specificity. A theory on selection consistency is established under certain regularity conditions.

Item Type: Article
DOI/Identification number: 10.1214/21-EJS1859
Uncontrolled keywords: Multivariate random-effects regression models, principal variable analysis, multivariate variable selection, null-beamforming
Subjects: Q Science > QA Mathematics (inc Computing science)
Divisions: Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Mathematics, Statistics and Actuarial Science
Depositing User: Jian Zhang
Date Deposited: 19 Aug 2022 11:03 UTC
Last Modified: 19 Aug 2022 11:03 UTC
Resource URI: (The current URI for this page, for reference purposes)
Zhang, Jian:
  • Depositors only (login required):


Downloads per month over past year