Fence methods for backcross experiments

Thuan Nguyen, Jie Peng, Jiming Jiang

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Model search strategies play an important role in finding simultaneous susceptibility genes that are associated with a trait. More particularly, model selection via the information criteria, such as the BIC with modifications, have received considerable attention in quantitative trait loci mapping. However, such modifications often depend upon several factors, such as sample size, prior distribution, and the type of experiment, for example, backcross, intercross. These changes make it difficult to generalize the methods to all cases. The fence method avoids such limitations with a unified approach, and hence can be used more broadly. In this article, this method is studied in the case of backcross experiments throughout a series of simulation studies. The results are compared with those of the modified BIC method as well as some of the most popular shrinkage methods for model selection.

Original languageEnglish (US)
Pages (from-to)644-662
Number of pages19
JournalJournal of Statistical Computation and Simulation
Volume84
Issue number3
DOIs
StatePublished - Mar 2014

Fingerprint

Fences
Experiment
Model Selection
Experiments
Quantitative Trait Loci
Genes
Information Criterion
Search Strategy
Shrinkage
Prior distribution
Susceptibility
Sample Size
Simulation Study
Gene
Generalise
Series

Keywords

  • high-dimensional variable selection
  • model selection
  • restricted fence

ASJC Scopus subject areas

  • Applied Mathematics
  • Statistics and Probability
  • Modeling and Simulation
  • Statistics, Probability and Uncertainty

Cite this

Fence methods for backcross experiments. / Nguyen, Thuan; Peng, Jie; Jiang, Jiming.

In: Journal of Statistical Computation and Simulation, Vol. 84, No. 3, 03.2014, p. 644-662.

Research output: Contribution to journalArticle

Nguyen, Thuan ; Peng, Jie ; Jiang, Jiming. / Fence methods for backcross experiments. In: Journal of Statistical Computation and Simulation. 2014 ; Vol. 84, No. 3. pp. 644-662.
@article{17fb8e6e43e94b18a99ec8908fbcbc64,
title = "Fence methods for backcross experiments",
abstract = "Model search strategies play an important role in finding simultaneous susceptibility genes that are associated with a trait. More particularly, model selection via the information criteria, such as the BIC with modifications, have received considerable attention in quantitative trait loci mapping. However, such modifications often depend upon several factors, such as sample size, prior distribution, and the type of experiment, for example, backcross, intercross. These changes make it difficult to generalize the methods to all cases. The fence method avoids such limitations with a unified approach, and hence can be used more broadly. In this article, this method is studied in the case of backcross experiments throughout a series of simulation studies. The results are compared with those of the modified BIC method as well as some of the most popular shrinkage methods for model selection.",
keywords = "high-dimensional variable selection, model selection, restricted fence",
author = "Thuan Nguyen and Jie Peng and Jiming Jiang",
year = "2014",
month = "3",
doi = "10.1080/00949655.2012.721885",
language = "English (US)",
volume = "84",
pages = "644--662",
journal = "Journal of Statistical Computation and Simulation",
issn = "0094-9655",
publisher = "Taylor and Francis Ltd.",
number = "3",

}

TY - JOUR

T1 - Fence methods for backcross experiments

AU - Nguyen, Thuan

AU - Peng, Jie

AU - Jiang, Jiming

PY - 2014/3

Y1 - 2014/3

N2 - Model search strategies play an important role in finding simultaneous susceptibility genes that are associated with a trait. More particularly, model selection via the information criteria, such as the BIC with modifications, have received considerable attention in quantitative trait loci mapping. However, such modifications often depend upon several factors, such as sample size, prior distribution, and the type of experiment, for example, backcross, intercross. These changes make it difficult to generalize the methods to all cases. The fence method avoids such limitations with a unified approach, and hence can be used more broadly. In this article, this method is studied in the case of backcross experiments throughout a series of simulation studies. The results are compared with those of the modified BIC method as well as some of the most popular shrinkage methods for model selection.

AB - Model search strategies play an important role in finding simultaneous susceptibility genes that are associated with a trait. More particularly, model selection via the information criteria, such as the BIC with modifications, have received considerable attention in quantitative trait loci mapping. However, such modifications often depend upon several factors, such as sample size, prior distribution, and the type of experiment, for example, backcross, intercross. These changes make it difficult to generalize the methods to all cases. The fence method avoids such limitations with a unified approach, and hence can be used more broadly. In this article, this method is studied in the case of backcross experiments throughout a series of simulation studies. The results are compared with those of the modified BIC method as well as some of the most popular shrinkage methods for model selection.

KW - high-dimensional variable selection

KW - model selection

KW - restricted fence

UR - http://www.scopus.com/inward/record.url?scp=84889257742&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84889257742&partnerID=8YFLogxK

U2 - 10.1080/00949655.2012.721885

DO - 10.1080/00949655.2012.721885

M3 - Article

VL - 84

SP - 644

EP - 662

JO - Journal of Statistical Computation and Simulation

JF - Journal of Statistical Computation and Simulation

SN - 0094-9655

IS - 3

ER -