Influence analysis in quantitative trait loci detection

Xiaoling Dou; Satoshi Kuriki; Akiteru Maeno; Toyoyuki Takada; Toshihiko Shiroishi

doi:10.1002/bimj.201200178

Influence analysis in quantitative trait loci detection

Xiaoling Dou^*, Satoshi Kuriki, Akiteru Maeno, Toyoyuki Takada, Toshihiko Shiroishi

^*Corresponding author for this work

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

Abstract

This paper presents systematic methods for the detection of influential individuals that affect the log odds (LOD) score curve. We derive general formulas of influence functions for profile likelihoods and introduce them into two standard quantitative trait locus detection methods-the interval mapping method and single marker analysis. Besides influence analysis on specific LOD scores, we also develop influence analysis methods on the shape of the LOD score curves. A simulation-based method is proposed to assess the significance of the influence of the individuals. These methods are shown useful in the influence analysis of a real dataset of an experimental population from an F₂ mouse cross. By receiver operating characteristic analysis, we confirm that the proposed methods show better performance than existing diagnostics.

Original language	English
Pages (from-to)	697-719
Number of pages	23
Journal	Biometrical Journal
Volume	56
Issue number	4
DOIs	https://doi.org/10.1002/bimj.201200178
Publication status	Published - 2014 Jun
Externally published	Yes

Keywords

Influence score vector
Profile likelihood
ROC analysis
Shape of LOD score curve
Standardized empirical influence function

ASJC Scopus subject areas

Statistics and Probability
Statistics, Probability and Uncertainty

Access to Document

10.1002/bimj.201200178

Cite this

@article{88ce6cfcaef04351ac6e2ebfdeb2b859,

title = "Influence analysis in quantitative trait loci detection",

abstract = "This paper presents systematic methods for the detection of influential individuals that affect the log odds (LOD) score curve. We derive general formulas of influence functions for profile likelihoods and introduce them into two standard quantitative trait locus detection methods-the interval mapping method and single marker analysis. Besides influence analysis on specific LOD scores, we also develop influence analysis methods on the shape of the LOD score curves. A simulation-based method is proposed to assess the significance of the influence of the individuals. These methods are shown useful in the influence analysis of a real dataset of an experimental population from an F2 mouse cross. By receiver operating characteristic analysis, we confirm that the proposed methods show better performance than existing diagnostics.",

keywords = "Influence score vector, Profile likelihood, ROC analysis, Shape of LOD score curve, Standardized empirical influence function",

author = "Xiaoling Dou and Satoshi Kuriki and Akiteru Maeno and Toyoyuki Takada and Toshihiko Shiroishi",

year = "2014",

month = jun,

doi = "10.1002/bimj.201200178",

language = "English",

volume = "56",

pages = "697--719",

journal = "Biometrische Zeitschrift",

issn = "0323-3847",

publisher = "Wiley-VCH Verlag",

number = "4",

}

TY - JOUR

T1 - Influence analysis in quantitative trait loci detection

AU - Dou, Xiaoling

AU - Kuriki, Satoshi

AU - Maeno, Akiteru

AU - Takada, Toyoyuki

AU - Shiroishi, Toshihiko

PY - 2014/6

Y1 - 2014/6

N2 - This paper presents systematic methods for the detection of influential individuals that affect the log odds (LOD) score curve. We derive general formulas of influence functions for profile likelihoods and introduce them into two standard quantitative trait locus detection methods-the interval mapping method and single marker analysis. Besides influence analysis on specific LOD scores, we also develop influence analysis methods on the shape of the LOD score curves. A simulation-based method is proposed to assess the significance of the influence of the individuals. These methods are shown useful in the influence analysis of a real dataset of an experimental population from an F2 mouse cross. By receiver operating characteristic analysis, we confirm that the proposed methods show better performance than existing diagnostics.

AB - This paper presents systematic methods for the detection of influential individuals that affect the log odds (LOD) score curve. We derive general formulas of influence functions for profile likelihoods and introduce them into two standard quantitative trait locus detection methods-the interval mapping method and single marker analysis. Besides influence analysis on specific LOD scores, we also develop influence analysis methods on the shape of the LOD score curves. A simulation-based method is proposed to assess the significance of the influence of the individuals. These methods are shown useful in the influence analysis of a real dataset of an experimental population from an F2 mouse cross. By receiver operating characteristic analysis, we confirm that the proposed methods show better performance than existing diagnostics.

KW - Influence score vector

KW - Profile likelihood

KW - ROC analysis

KW - Shape of LOD score curve

KW - Standardized empirical influence function

UR - http://www.scopus.com/inward/record.url?scp=84903604838&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903604838&partnerID=8YFLogxK

U2 - 10.1002/bimj.201200178

DO - 10.1002/bimj.201200178

M3 - Article

C2 - 24740424

AN - SCOPUS:84903604838

SN - 0323-3847

VL - 56

SP - 697

EP - 719

JO - Biometrische Zeitschrift

JF - Biometrische Zeitschrift

IS - 4

ER -

Influence analysis in quantitative trait loci detection

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this