Variable selection for partially linear models via partial correlation

Jingyuan Liu, Lejia Lou, Runze Li

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

The partially linear model (PLM) is a useful semiparametric extension of the linear model that has been well studied in the statistical literature. This paper proposes a variable selection procedure for the PLM with ultrahigh dimensional predictors. The proposed method is different from the existing penalized least squares procedure in that it relies on partial correlation between the partial residuals of the response and the predictors. We systematically study the theoretical properties of the proposed procedure and prove its model consistency property. We further establish the root-n convergence of the estimator of the regression coefficients and the asymptotic normality of the estimate of the baseline function. We conduct Monte Carlo simulations to examine the finite-sample performance of the proposed procedure and illustrate the proposed method with a real data example.

Original languageEnglish (US)
Pages (from-to)418-434
Number of pages17
JournalJournal of Multivariate Analysis
Volume167
DOIs
StatePublished - Sep 1 2018

Fingerprint

Partially Linear Model
Partial Correlation
Variable Selection
Predictors
Penalized Least Squares
Selection Procedures
Regression Coefficient
Asymptotic Normality
Baseline
Linear Model
Monte Carlo Simulation
Roots
Estimator
Partial
Estimate
Partially linear model
Variable selection
Model

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Numerical Analysis
  • Statistics, Probability and Uncertainty

Cite this

@article{3c584ff4807c4505ba840faea6cd552b,
title = "Variable selection for partially linear models via partial correlation",
abstract = "The partially linear model (PLM) is a useful semiparametric extension of the linear model that has been well studied in the statistical literature. This paper proposes a variable selection procedure for the PLM with ultrahigh dimensional predictors. The proposed method is different from the existing penalized least squares procedure in that it relies on partial correlation between the partial residuals of the response and the predictors. We systematically study the theoretical properties of the proposed procedure and prove its model consistency property. We further establish the root-n convergence of the estimator of the regression coefficients and the asymptotic normality of the estimate of the baseline function. We conduct Monte Carlo simulations to examine the finite-sample performance of the proposed procedure and illustrate the proposed method with a real data example.",
author = "Jingyuan Liu and Lejia Lou and Runze Li",
year = "2018",
month = "9",
day = "1",
doi = "10.1016/j.jmva.2018.06.005",
language = "English (US)",
volume = "167",
pages = "418--434",
journal = "Journal of Multivariate Analysis",
issn = "0047-259X",
publisher = "Academic Press Inc.",

}

Variable selection for partially linear models via partial correlation. / Liu, Jingyuan; Lou, Lejia; Li, Runze.

In: Journal of Multivariate Analysis, Vol. 167, 01.09.2018, p. 418-434.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Variable selection for partially linear models via partial correlation

AU - Liu, Jingyuan

AU - Lou, Lejia

AU - Li, Runze

PY - 2018/9/1

Y1 - 2018/9/1

N2 - The partially linear model (PLM) is a useful semiparametric extension of the linear model that has been well studied in the statistical literature. This paper proposes a variable selection procedure for the PLM with ultrahigh dimensional predictors. The proposed method is different from the existing penalized least squares procedure in that it relies on partial correlation between the partial residuals of the response and the predictors. We systematically study the theoretical properties of the proposed procedure and prove its model consistency property. We further establish the root-n convergence of the estimator of the regression coefficients and the asymptotic normality of the estimate of the baseline function. We conduct Monte Carlo simulations to examine the finite-sample performance of the proposed procedure and illustrate the proposed method with a real data example.

AB - The partially linear model (PLM) is a useful semiparametric extension of the linear model that has been well studied in the statistical literature. This paper proposes a variable selection procedure for the PLM with ultrahigh dimensional predictors. The proposed method is different from the existing penalized least squares procedure in that it relies on partial correlation between the partial residuals of the response and the predictors. We systematically study the theoretical properties of the proposed procedure and prove its model consistency property. We further establish the root-n convergence of the estimator of the regression coefficients and the asymptotic normality of the estimate of the baseline function. We conduct Monte Carlo simulations to examine the finite-sample performance of the proposed procedure and illustrate the proposed method with a real data example.

UR - http://www.scopus.com/inward/record.url?scp=85049323672&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049323672&partnerID=8YFLogxK

U2 - 10.1016/j.jmva.2018.06.005

DO - 10.1016/j.jmva.2018.06.005

M3 - Article

C2 - 31182883

AN - SCOPUS:85049323672

VL - 167

SP - 418

EP - 434

JO - Journal of Multivariate Analysis

JF - Journal of Multivariate Analysis

SN - 0047-259X

ER -