On the Comparison of Classifiers for Microarray Data Academic Article

abstract

• The aim of many microarray experiments is to build discriminatory diagnosis and prognosis models. A large number of supervised methods have been proposed in literature for microarray-based classification. Model comparison, which is based on the classification error estimation, is a critical issue. Previous studies have shown that error estimation is unreliable in high-dimensional small-sample settings. This leads naturally to questioning the validity of classificationrule comparison approaches being used in the literature. In this paper we present a brief review of the different comparison methods used in bioinformatics. Then, we test these methods on a set of simulations based on both synthetic and real data. These simulations include different feature-label distributions, classification rules, error estimators and variance estimators. The results show that none of these methods can provide reliable comparison across a wide spectrum of feature-label distributions and classification rules. 2010 Bentham Science Publishers Ltd.

authors

• Dougherty, Edward

published proceedings

• CURRENT BIOINFORMATICS

author list (cited authors)

• Hanczar, B., & Dougherty, E. R.

citation count

• 13

complete list of authors

• Hanczar, Blaise||Dougherty, Edward R

publication date

• March 2010

publisher

• BENTHAM SCIENCE PUBLISHERS  Publisher

published in

• Current Bioinformatics  Journal

keywords

• Classifier Comparison
• Error Estimation
• Microarray Classification
• Variance Study

Digital Object Identifier (DOI)

• 10.2174/157489310790596376

start page

• 29

end page

• 39

volume

• 5

issue

• 1

URL

• http%3A%2F%2Fdx.doi.org%2F10.2174%2F157489310790596376