Skip Navigation



Bioinformatics Advance Access published online on February 24, 2006
Bioinformatics, doi:10.1093/bioinformatics/btl066
This Article
Right arrow Advance Access manuscript (PDF) Freely available
Right arrowOA All Versions of this Article:
22/10/1245    most recent
btl066v1
Right arrow Comments: Submit a response
Right arrow Alert me when this article is cited
Right arrow Alert me when Comments are posted
Right arrow Alert me if a correction is posted
Services
Right arrow Email this article to a friend
Right arrow Similar articles in this journal
Right arrow Similar articles in PubMed
Right arrow Alert me to new issues of the journal
Right arrow Add to My Personal Archive
Right arrow Download to citation manager
Google Scholar
Right arrow Articles by Berrar, D.
Right arrow Articles by Dubitzky, W.
Right arrow Search for Related Content
PubMed
Right arrow PubMed Citation
Right arrow Articles by Berrar, D.
Right arrow Articles by Dubitzky, W.
Social Bookmarking
Add to CiteULike   Add to Connotea   Add to Del.icio.us  
What's this?

© The Author (2006). Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oxfordjournals.org
Received October 19, 2005
Revised January 29, 2006
Accepted February 20, 2006

Article

Avoiding model selection bias in small-sample genomic data sets

Daniel Berrar 1 *, Ian Bradbury 1, and Werner Dubitzky 1

1 School of Biomedical Sciences, University of Ulster at Coleraine, Northern Ireland

* To whom correspondence should be addressed.
Daniel Berrar, E-mail: dp.berrar{at}ulster.ac.uk


  Abstract

Motivation: Genomic data sets generated by high-throughput technologies are typically characterized by a moderate number of samples and a large number of measurements per sample. As a consequence, classification models are commonly compared based on resampling techniques. This investigation discusses the conceptual difficulties involved in comparative classification studies. Conclusions derived from such studies are often optimistically biased, because the apparent differences in performance are usually not controlled in a statistically stringent framework taking into account the adopted sampling strategy. We investigate this problem by means of a comparison of various classifiers in the context of multiclass microarray data.

Results: Commonly used accuracy-based performance values, with or without confidence intervals, are inadequate for comparing classifiers for small-sample data. We present a statistical methodology that avoids bias in cross-validated model selection in the context of small-sample scenarios. This methodology is valid for both k-fold cross-validation and repeated random sampling.

Associate Editor: Joaquin Dopazo
Add to CiteULike CiteULike   Add to Connotea Connotea   Add to Del.icio.us Del.icio.us    What's this?


This article has been cited by other articles:


Home page
 BioinformaticsHome page
S. Sundaresh, A. Randall, B. Unal, J. M. Petersen, J. T. Belisle, M. Gill Hartley, M. Duffield, R. W. Titball, D. H. Davies, P. L. Felgner, et al.
From protein microarrays to diagnostic antigen discovery: a study of the pathogen Francisella tularensis
Bioinformatics, July 1, 2007; 23(13): i508 - i518.
[Abstract] [Full Text] [PDF]


Disclaimer: Please note that abstracts for content published before 1996 were created through digital scanning and may therefore not exactly replicate the text of the original print issues. All efforts have been made to ensure accuracy, but the Publisher will not be held responsible for any remaining inaccuracies. If you require any further clarification, please contact our Customer Services Department.