Profiled adaptive Elastic-Net procedure for partially linear models with high-dimensional covariates

Baicheng Chen; Yao Yu; Hui Zou; Hua Liang

doi:10.1016/j.jspi.2012.02.035

Profiled adaptive Elastic-Net procedure for partially linear models with high-dimensional covariates

Baicheng Chen, Yao Yu, Hui Zou, Hua Liang

Statistics (Twin Cities)

Research output: Contribution to journal › Article › peer-review

8 Scopus citations

Abstract

We study variable selection for partially linear models when the dimension of covariates diverges with the sample size. We combine the ideas of profiling and adaptive Elastic-Net. The resulting procedure has oracle properties and can handle collinearity well. A by-product is the uniform bound for the absolute difference between the profiled and original predictors. We further examine finite sample performance of the proposed procedure by simulation studies and analysis of a labor-market dataset for an illustration.

Original language	English (US)
Pages (from-to)	1733-1745
Number of pages	13
Journal	Journal of Statistical Planning and Inference
Volume	142
Issue number	7
DOIs	https://doi.org/10.1016/j.jspi.2012.02.035
State	Published - Jul 2012

Bibliographical note

Funding Information:
Liang's research was partially supported by NSF grant DMS-1007167 .

Keywords

Adaptive regularization
Elastic-Net
High dimensionality
Model selection
Oracle property
Presmoothing
Semiparametric model
Shrinkage methods

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Publisher link

10.1016/j.jspi.2012.02.035

Find It

Find It at U of M Libraries

Cite this

@article{04373203050b402abc3646fbeb3d7b07,

title = "Profiled adaptive Elastic-Net procedure for partially linear models with high-dimensional covariates",

abstract = "We study variable selection for partially linear models when the dimension of covariates diverges with the sample size. We combine the ideas of profiling and adaptive Elastic-Net. The resulting procedure has oracle properties and can handle collinearity well. A by-product is the uniform bound for the absolute difference between the profiled and original predictors. We further examine finite sample performance of the proposed procedure by simulation studies and analysis of a labor-market dataset for an illustration.",

keywords = "Adaptive regularization, Elastic-Net, High dimensionality, Model selection, Oracle property, Presmoothing, Semiparametric model, Shrinkage methods",

author = "Baicheng Chen and Yao Yu and Hui Zou and Hua Liang",

note = "Funding Information: Liang's research was partially supported by NSF grant DMS-1007167 . ",

year = "2012",

month = jul,

doi = "10.1016/j.jspi.2012.02.035",

language = "English (US)",

volume = "142",

pages = "1733--1745",

journal = "Journal of Statistical Planning and Inference",

issn = "0378-3758",

publisher = "Elsevier",

number = "7",

}

TY - JOUR

T1 - Profiled adaptive Elastic-Net procedure for partially linear models with high-dimensional covariates

AU - Chen, Baicheng

AU - Yu, Yao

AU - Zou, Hui

AU - Liang, Hua

N1 - Funding Information: Liang's research was partially supported by NSF grant DMS-1007167 .

PY - 2012/7

Y1 - 2012/7

N2 - We study variable selection for partially linear models when the dimension of covariates diverges with the sample size. We combine the ideas of profiling and adaptive Elastic-Net. The resulting procedure has oracle properties and can handle collinearity well. A by-product is the uniform bound for the absolute difference between the profiled and original predictors. We further examine finite sample performance of the proposed procedure by simulation studies and analysis of a labor-market dataset for an illustration.

AB - We study variable selection for partially linear models when the dimension of covariates diverges with the sample size. We combine the ideas of profiling and adaptive Elastic-Net. The resulting procedure has oracle properties and can handle collinearity well. A by-product is the uniform bound for the absolute difference between the profiled and original predictors. We further examine finite sample performance of the proposed procedure by simulation studies and analysis of a labor-market dataset for an illustration.

KW - Adaptive regularization

KW - Elastic-Net

KW - High dimensionality

KW - Model selection

KW - Oracle property

KW - Presmoothing

KW - Semiparametric model

KW - Shrinkage methods

UR - http://www.scopus.com/inward/record.url?scp=84862826361&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862826361&partnerID=8YFLogxK

U2 - 10.1016/j.jspi.2012.02.035

DO - 10.1016/j.jspi.2012.02.035

M3 - Article

AN - SCOPUS:84862826361

SN - 0378-3758

VL - 142

SP - 1733

EP - 1745

JO - Journal of Statistical Planning and Inference

JF - Journal of Statistical Planning and Inference

IS - 7

ER -

Profiled adaptive Elastic-Net procedure for partially linear models with high-dimensional covariates

Abstract

Bibliographical note

Keywords

UN SDGs

Publisher link

Find It

Other files and links

Fingerprint

Cite this