Restricted fence method for covariate selection in longitudinal data analysis

Thuan Nguyen, Jiming Jiang

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Fence method (Jiang and others 2008. Fence methods for mixed model selection. Annals of Statistics 36, 1669-1692) is a recently proposed strategy for model selection. It was motivated by the limitation of the traditional information criteria in selecting parsimonious models in some nonconventional situations, such as mixed model selection. Jiang and others (2009. A simplified adaptive fence procedure, Statistics & Probability Letters 79, 625-629) simplified the adaptive fence method of Jiang and others (2008) to make it more suitable and convenient to use in a wide variety of problems. Still, the current modification encounters computational difficulties when applied to high-dimensional and complex problems. To address this concern, we proposed a restricted fence procedure that combines the idea of the fence with that of the restricted maximum likelihood. Furthermore, we propose to use the wild bootstrap for choosing adaptively the tuning parameter used in the restricted fence. We focus on problems of longitudinal studies and demonstrate the performance of the new procedure and its comparison with other procedures of variable selection, including the information criteria and shrinkage methods, in simulation studies. The method is further illustrated by an example of real-data analysis.

Original languageEnglish (US)
Pages (from-to)303-314
Number of pages12
JournalBiostatistics
Volume13
Issue number2
DOIs
StatePublished - Apr 2012

Fingerprint

Longitudinal Data Analysis
Covariates
Model Selection
Information Criterion
Mixed Model
Wild Bootstrap
Statistics
Restricted Maximum Likelihood
Selection of Variables
Adaptive Procedure
Longitudinal Study
Parameter Tuning
Adaptive Method
Shrinkage
Data analysis
High-dimensional
Simulation Study
Longitudinal data analysis
Demonstrate
Longitudinal Studies

Keywords

  • Covariate variable selection
  • Longitudinal data
  • Restricted fence method
  • Wild boostrapping

ASJC Scopus subject areas

  • Medicine(all)
  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Restricted fence method for covariate selection in longitudinal data analysis. / Nguyen, Thuan; Jiang, Jiming.

In: Biostatistics, Vol. 13, No. 2, 04.2012, p. 303-314.

Research output: Contribution to journalArticle

@article{39585fe8bf1e4c3dafa22114bef6d6e0,
title = "Restricted fence method for covariate selection in longitudinal data analysis",
abstract = "Fence method (Jiang and others 2008. Fence methods for mixed model selection. Annals of Statistics 36, 1669-1692) is a recently proposed strategy for model selection. It was motivated by the limitation of the traditional information criteria in selecting parsimonious models in some nonconventional situations, such as mixed model selection. Jiang and others (2009. A simplified adaptive fence procedure, Statistics & Probability Letters 79, 625-629) simplified the adaptive fence method of Jiang and others (2008) to make it more suitable and convenient to use in a wide variety of problems. Still, the current modification encounters computational difficulties when applied to high-dimensional and complex problems. To address this concern, we proposed a restricted fence procedure that combines the idea of the fence with that of the restricted maximum likelihood. Furthermore, we propose to use the wild bootstrap for choosing adaptively the tuning parameter used in the restricted fence. We focus on problems of longitudinal studies and demonstrate the performance of the new procedure and its comparison with other procedures of variable selection, including the information criteria and shrinkage methods, in simulation studies. The method is further illustrated by an example of real-data analysis.",
keywords = "Covariate variable selection, Longitudinal data, Restricted fence method, Wild boostrapping",
author = "Thuan Nguyen and Jiming Jiang",
year = "2012",
month = "4",
doi = "10.1093/biostatistics/kxr046",
language = "English (US)",
volume = "13",
pages = "303--314",
journal = "Biostatistics",
issn = "1465-4644",
publisher = "Oxford University Press",
number = "2",

}

TY - JOUR

T1 - Restricted fence method for covariate selection in longitudinal data analysis

AU - Nguyen, Thuan

AU - Jiang, Jiming

PY - 2012/4

Y1 - 2012/4

N2 - Fence method (Jiang and others 2008. Fence methods for mixed model selection. Annals of Statistics 36, 1669-1692) is a recently proposed strategy for model selection. It was motivated by the limitation of the traditional information criteria in selecting parsimonious models in some nonconventional situations, such as mixed model selection. Jiang and others (2009. A simplified adaptive fence procedure, Statistics & Probability Letters 79, 625-629) simplified the adaptive fence method of Jiang and others (2008) to make it more suitable and convenient to use in a wide variety of problems. Still, the current modification encounters computational difficulties when applied to high-dimensional and complex problems. To address this concern, we proposed a restricted fence procedure that combines the idea of the fence with that of the restricted maximum likelihood. Furthermore, we propose to use the wild bootstrap for choosing adaptively the tuning parameter used in the restricted fence. We focus on problems of longitudinal studies and demonstrate the performance of the new procedure and its comparison with other procedures of variable selection, including the information criteria and shrinkage methods, in simulation studies. The method is further illustrated by an example of real-data analysis.

AB - Fence method (Jiang and others 2008. Fence methods for mixed model selection. Annals of Statistics 36, 1669-1692) is a recently proposed strategy for model selection. It was motivated by the limitation of the traditional information criteria in selecting parsimonious models in some nonconventional situations, such as mixed model selection. Jiang and others (2009. A simplified adaptive fence procedure, Statistics & Probability Letters 79, 625-629) simplified the adaptive fence method of Jiang and others (2008) to make it more suitable and convenient to use in a wide variety of problems. Still, the current modification encounters computational difficulties when applied to high-dimensional and complex problems. To address this concern, we proposed a restricted fence procedure that combines the idea of the fence with that of the restricted maximum likelihood. Furthermore, we propose to use the wild bootstrap for choosing adaptively the tuning parameter used in the restricted fence. We focus on problems of longitudinal studies and demonstrate the performance of the new procedure and its comparison with other procedures of variable selection, including the information criteria and shrinkage methods, in simulation studies. The method is further illustrated by an example of real-data analysis.

KW - Covariate variable selection

KW - Longitudinal data

KW - Restricted fence method

KW - Wild boostrapping

UR - http://www.scopus.com/inward/record.url?scp=84858055972&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84858055972&partnerID=8YFLogxK

U2 - 10.1093/biostatistics/kxr046

DO - 10.1093/biostatistics/kxr046

M3 - Article

C2 - 22180413

AN - SCOPUS:84858055972

VL - 13

SP - 303

EP - 314

JO - Biostatistics

JF - Biostatistics

SN - 1465-4644

IS - 2

ER -