TY - JOUR
T1 - Selecting genes by test statistics
AU - Chen, Dechang
AU - Liu, Zhenqiu
AU - Ma, Xiaobin
AU - Hua, Dong
N1 - Funding Information:
Chen Dechang [email protected] 1 Liu Zhenqiu 2 Ma Xiaobin 3 Hua Dong 4 1 Division of Epidemiology and Biostatistics Uniformed Services University of the Health Sciences 4301 Jones Bridge Road Bethesda, MD 20814 USA usuhs.mil 2 Bioinformatics Cell TATRC 110 North Market Street Frederick, MD 21703 USA tatrc.org 3 Department of Computer Science and Engineering University of Minnesota 200 Union Street SE Minneapolis, MN 55455 USA umn.edu 4 Department of Computer Science The George Washington University 801 22nd St. NW Washington, DC 20052 USA gwu.edu 2005 30 06 2005 2005 2 132 138 28 04 2004 23 11 2004 22 11 2004 2005 Copyright © 2005 Hindawi Publishing Corporation. This is an open access article distributed under the Creative Commons Attribution License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Gene selection is an important issue in analyzing multiclass microarray data. Among many proposed selection methods, the traditional ANOVA F test statistic has been employed to identify informative genes for both class prediction (classification) and discovery problems. However, the F test statistic assumes an equal variance. This assumption may not be realistic for gene expression data. This paper explores other alternative test statistics which can handle heterogeneity of the variances. We study five such test statistics, which include Brown-Forsythe test statistic and Welch test statistic. Their performance is evaluated and compared with that of F statistic over different classification methods applied to publicly available microarray datasets. http://dx.doi.org/10.13039/100000001 National Science Foundation CCR-0311252
PY - 2005/6/30
Y1 - 2005/6/30
N2 - Gene selection is an important issue in analyzing multiclass microarray data. Among many proposed selection methods, the traditional ANOVA F test statistic has been employed to identify informative genes for both class prediction (classification) and discovery problems. However, the F test statistic assumes an equal variance. This assumption may not be realistic for gene expression data. This paper explores other alternative test statistics which can handle heterogeneity of the variances. We study five such test statistics, which include Brown-Forsythe test statistic and Welch test statistic. Their performance is evaluated and compared with that of F statistic over different classification methods applied to publicly available microarray datasets.
AB - Gene selection is an important issue in analyzing multiclass microarray data. Among many proposed selection methods, the traditional ANOVA F test statistic has been employed to identify informative genes for both class prediction (classification) and discovery problems. However, the F test statistic assumes an equal variance. This assumption may not be realistic for gene expression data. This paper explores other alternative test statistics which can handle heterogeneity of the variances. We study five such test statistics, which include Brown-Forsythe test statistic and Welch test statistic. Their performance is evaluated and compared with that of F statistic over different classification methods applied to publicly available microarray datasets.
UR - http://www.scopus.com/inward/record.url?scp=27744557285&partnerID=8YFLogxK
U2 - 10.1155/JBB.2005.132
DO - 10.1155/JBB.2005.132
M3 - Article
AN - SCOPUS:27744557285
SN - 1110-7243
VL - 2005
SP - 132
EP - 138
JO - Journal of Biomedicine and Biotechnology
JF - Journal of Biomedicine and Biotechnology
IS - 2
ER -