On the alleviation of side effect of outliers to Fisher's Discriminate Criterion in micro-array data analysis

Kajia Cao, Qiuming Zhu, Javeed Iqbal, John W.C. Chan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The use of Fisher's Discriminate Criterion (FDC) is studied for extracting genes that are predictive to BCL2 translocations of diffuse large B-cell lymphoma (DLBCL) from DNA micro-array gene expression profiling. It is found that the FDC is easily to be biased and distorted by the uncertainty of the outliers in the data in terms of its statistical characteristics. In this paper, some experiments on finding and eliminating certain side effects of outliers in the DLBCL data for FDC-based analysis are described. The results of the experimentation are presented.

Original languageEnglish (US)
Title of host publicationProceedings of the International Conference on Mathematics and Engineering Techniques in Medicine and Biological Sciences, METMBS'04
EditorsF. Valafar, H. Valafar
Pages263-269
Number of pages7
StatePublished - 2004
EventProceedings of the International Conference on Mathematics and Engineering Techniques in medicine and Biological Sciences, METMBS'04 - Las Vegas, NV, United States
Duration: Jun 21 2004Jun 24 2004

Publication series

NameProceedings of the International Conference on Mathematics and Engineering Techniques in Medicine and Biological Sciences, METMBS'04

Conference

ConferenceProceedings of the International Conference on Mathematics and Engineering Techniques in medicine and Biological Sciences, METMBS'04
Country/TerritoryUnited States
CityLas Vegas, NV
Period6/21/046/24/04

Keywords

  • Classifications
  • Fisher's Discriminate Criterion (FDC)
  • Gene expression profiling
  • Micro-array data analysis
  • Outlier

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'On the alleviation of side effect of outliers to Fisher's Discriminate Criterion in micro-array data analysis'. Together they form a unique fingerprint.

Cite this