Weighted wilcoxon-type smoothly clipped absolute deviation method

Lan Wang, Runze Li

Research output: Contribution to journalArticle

35 Citations (Scopus)

Abstract

Shrinkage-type variable selection procedures have recently seen increasing applications in biomedical research. However, their performance can be adversely influenced by outliers in either the response or the covariate space. This article proposes a weighted Wilcoxon-type smoothly clipped absolute deviation (WW-SCAD) method, which deals with robust variable selection and robust estimation simultaneously. The new procedure can be conveniently implemented with the statistical software R. We establish that the WW-SCAD correctly identifies the set of zero coefficients with probability approaching one and estimates the nonzero coefficients with the rate n-1/2. Moreover, with appropriately chosen weights the WW-SCAD is robust with respect to outliers in both the x and y directions. The important special case with constant weights yields an oracle-type estimator with high efficiency in the presence of heavier-tailed random errors. The robustness of the WW-SCAD is partly justified by its asymptotic performance under local shrinking contamination. We propose a Bayesian information criterion type tuning parameter selector for the WW-SCAD. The performance of the WW-SCAD is demonstrated via simulations and by an application to a study that investigates the effects of personal characteristics and dietary factors on plasma beta-carotene level.

Original languageEnglish (US)
Pages (from-to)564-571
Number of pages8
JournalBiometrics
Volume65
Issue number2
DOIs
StatePublished - Jun 1 2009

Fingerprint

Deviation
Random errors
biomedical research
beta Carotene
shrinkage
beta-carotene
Weights and Measures
Contamination
Tuning
Variable Selection
Plasmas
Outlier
Biomedical Research
Software
methodology
diet
y direction
x direction
Bayesian Information Criterion
Statistical Software

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Biochemistry, Genetics and Molecular Biology(all)
  • Immunology and Microbiology(all)
  • Agricultural and Biological Sciences(all)
  • Applied Mathematics

Cite this

@article{fb64f5a3149d4faea97a11b65dfc494d,
title = "Weighted wilcoxon-type smoothly clipped absolute deviation method",
abstract = "Shrinkage-type variable selection procedures have recently seen increasing applications in biomedical research. However, their performance can be adversely influenced by outliers in either the response or the covariate space. This article proposes a weighted Wilcoxon-type smoothly clipped absolute deviation (WW-SCAD) method, which deals with robust variable selection and robust estimation simultaneously. The new procedure can be conveniently implemented with the statistical software R. We establish that the WW-SCAD correctly identifies the set of zero coefficients with probability approaching one and estimates the nonzero coefficients with the rate n-1/2. Moreover, with appropriately chosen weights the WW-SCAD is robust with respect to outliers in both the x and y directions. The important special case with constant weights yields an oracle-type estimator with high efficiency in the presence of heavier-tailed random errors. The robustness of the WW-SCAD is partly justified by its asymptotic performance under local shrinking contamination. We propose a Bayesian information criterion type tuning parameter selector for the WW-SCAD. The performance of the WW-SCAD is demonstrated via simulations and by an application to a study that investigates the effects of personal characteristics and dietary factors on plasma beta-carotene level.",
author = "Lan Wang and Runze Li",
year = "2009",
month = "6",
day = "1",
doi = "10.1111/j.1541-0420.2008.01099.x",
language = "English (US)",
volume = "65",
pages = "564--571",
journal = "Biometrics",
issn = "0006-341X",
publisher = "Wiley-Blackwell",
number = "2",

}

Weighted wilcoxon-type smoothly clipped absolute deviation method. / Wang, Lan; Li, Runze.

In: Biometrics, Vol. 65, No. 2, 01.06.2009, p. 564-571.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Weighted wilcoxon-type smoothly clipped absolute deviation method

AU - Wang, Lan

AU - Li, Runze

PY - 2009/6/1

Y1 - 2009/6/1

N2 - Shrinkage-type variable selection procedures have recently seen increasing applications in biomedical research. However, their performance can be adversely influenced by outliers in either the response or the covariate space. This article proposes a weighted Wilcoxon-type smoothly clipped absolute deviation (WW-SCAD) method, which deals with robust variable selection and robust estimation simultaneously. The new procedure can be conveniently implemented with the statistical software R. We establish that the WW-SCAD correctly identifies the set of zero coefficients with probability approaching one and estimates the nonzero coefficients with the rate n-1/2. Moreover, with appropriately chosen weights the WW-SCAD is robust with respect to outliers in both the x and y directions. The important special case with constant weights yields an oracle-type estimator with high efficiency in the presence of heavier-tailed random errors. The robustness of the WW-SCAD is partly justified by its asymptotic performance under local shrinking contamination. We propose a Bayesian information criterion type tuning parameter selector for the WW-SCAD. The performance of the WW-SCAD is demonstrated via simulations and by an application to a study that investigates the effects of personal characteristics and dietary factors on plasma beta-carotene level.

AB - Shrinkage-type variable selection procedures have recently seen increasing applications in biomedical research. However, their performance can be adversely influenced by outliers in either the response or the covariate space. This article proposes a weighted Wilcoxon-type smoothly clipped absolute deviation (WW-SCAD) method, which deals with robust variable selection and robust estimation simultaneously. The new procedure can be conveniently implemented with the statistical software R. We establish that the WW-SCAD correctly identifies the set of zero coefficients with probability approaching one and estimates the nonzero coefficients with the rate n-1/2. Moreover, with appropriately chosen weights the WW-SCAD is robust with respect to outliers in both the x and y directions. The important special case with constant weights yields an oracle-type estimator with high efficiency in the presence of heavier-tailed random errors. The robustness of the WW-SCAD is partly justified by its asymptotic performance under local shrinking contamination. We propose a Bayesian information criterion type tuning parameter selector for the WW-SCAD. The performance of the WW-SCAD is demonstrated via simulations and by an application to a study that investigates the effects of personal characteristics and dietary factors on plasma beta-carotene level.

UR - http://www.scopus.com/inward/record.url?scp=66949149744&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=66949149744&partnerID=8YFLogxK

U2 - 10.1111/j.1541-0420.2008.01099.x

DO - 10.1111/j.1541-0420.2008.01099.x

M3 - Article

C2 - 18647294

AN - SCOPUS:66949149744

VL - 65

SP - 564

EP - 571

JO - Biometrics

JF - Biometrics

SN - 0006-341X

IS - 2

ER -