Feature selection increases cross-validation imprecision Conference Paper

abstract

• Even without feature selection, cross-validation error estimation is problematic for small samples owing to the high variance of the deviation distribution describing the difference between the estimated and true errors. This paper investigates the increased loss of cross-validation precision owing to feature selection by comparing deviation distributions and introducing two variation-based measures to quantify the further degradation in performance. 2006 IEEE.

name of conference

• 2006 IEEE International Workshop on Genomic Signal Processing and Statistics

authors

• Dougherty, Edward

published proceedings

• 2006 IEEE INTERNATIONAL WORKSHOP ON GENOMIC SIGNAL PROCESSING AND STATISTICS

author list (cited authors)

• Xiao, Y., Hua, J., & Dougherty, E. R.

citation count

• 1

complete list of authors

• Xiao, Yufei||Hua, Jianping||Dougherty, Edward R

publication date

• May 2006

publisher

• Institute of Electrical and Electronics Engineers (IEEE)  Publisher

published in

• IEEE International Workshop on Genomic Signal Processing and Statistics : [proceedings]. IEEE International Workshop on Genomic Signal Processing and Statistics  Journal

keywords

• 3 Good Health And Well Being
• 46 Information And Computing Sciences
• 49 Mathematical Sciences
• 4905 Statistics

Digital Object Identifier (DOI)

• 10.1109/GENSIPS.2006.353134

International Standard Book Number (ISBN) 10

• 1424403855

International Standard Book Number (ISBN) 13

• 978-1-4244-0384-4

start page

• 17

end page

• +

URL

• http://dx.doi.org/10.1109/gensips.2006.353134

user-defined tag

• 3 Good Health and Well-Being