This file is part of IDEAS, which uses RePEc data


[ Papers | Articles | Software | Books | Chapters | Authors | Institutions | JEL Classification | NEP reports | Search | New papers by email | Author registration | Rankings | Volunteers | FAQ | Blog | Help! ]

Tilting methods for assessing the influence of components in a classifier

Author info | Abstract | Publisher info | Download info | Related research | Statistics
Author Info
Peter Hall
D. M. Titterington
Jing-Hao Xue
Abstract

Many contemporary classifiers are constructed to provide good performance for very high dimensional data. However, an issue that is at least as important as good classification is determining which of the many potential variables provide key information for good decisions. Responding to this issue can help us to determine which aspects of the datagenerating mechanism (e.g. which genes in a genomic study) are of greatest importance in terms of distinguishing between populations. We introduce tilting methods for addressing this problem. We apply weights to the components of data vectors, rather than to the data vectors themselves (as is commonly the case in related work). In addition we tilt in a way that is governed by "L"2-distance between weight vectors, rather than by the more commonly used Kullback-Leibler distance. It is shown that this approach, together with the added constraint that the weights should be non-negative, produces an algorithm which eliminates vector components that have little influence on the classification decision. In particular, use of the "L"2-distance in this problem produces properties that are reminiscent of those that arise when "L"1-penalties are employed to eliminate explanatory variables in very high dimensional prediction problems, e.g. those involving the lasso. We introduce techniques that can be implemented very rapidly, and we show how to use bootstrap methods to assess the accuracy of our variable ranking and variable elimination procedures. Copyright (c) 2009 Royal Statistical Society.

Download Info
To download:

If you experience problems downloading a file, check if you have the proper application to view it first. Information about this may be contained in the File-Format links below. In case of further problems read the IDEAS help page. Note that these files are not on the IDEAS site. Please be patient as the files may be large.

File URL: http://www.blackwell-synergy.com/doi/abs/10.1111/j.1467-9868.2009.00701.x
File Format: text/html
File Function: link to full text
Download Restriction: Access to full text is restricted to subscribers.

As the access to this document is restricted, you may want to look for a different version under "Related research" (further below) or search for a different version of it.

Publisher Info
Article provided by Royal Statistical Society in its journal Journal of the Royal Statistical Society: Series B (Statistical Methodology).

Volume (Year): 71 (2009)
Issue (Month): 4 ()
Pages: 783-803
Download reference. The following formats are available: HTML (with abstract), plain text (with abstract), BibTeX, RIS (EndNote, RefMan, ProCite), ReDIF
Handle: RePEc:bla:jorssb:v:71:y:2009:i:4:p:783-803

Contact details of provider:
Web page: http://www.blackwellpublishing.com/journal.asp?ref=1369-7412

Order Information:
Web: http://www.blackwellpublishing.com/subs.asp?ref=1369-7412

For technical questions regarding this item, or to correct its listing, contact: (Christopher F. Baum).

Related research
Keywords:

Statistics
Access and download statistics

Did you know? You can create your own reading lists on IDEAS.

This page was last updated on 2009-12-19.


This information is provided to you by IDEAS at the Department of Economics, College of Liberal Arts and Sciences, University of Connecticut using RePEc data on a server sponsored by the Society for Economic Dynamics.