Tilting methods for assessing the influence of components in a classifier
AbstractMany 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 InfoIf you experience problems downloading a file, check if you have the proper application to view it first. 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.
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.
Bibliographic InfoArticle 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 ()
Contact details of provider:
Postal: 12 Errol Street, London EC1Y 8LX, United Kingdom
Web page: http://wileyonlinelibrary.com/journal/rssb
More information through EDIRC
You can help add them by filling out this form.
CitEc Project, subscribe to its RSS feed for this item.
- Hall, Peter & Xue, Jing-Hao, 2014. "On selecting interacting features from high-dimensional data," Computational Statistics & Data Analysis, Elsevier, Elsevier, vol. 71(C), pages 694-708.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Wiley-Blackwell Digital Licensing) or (Christopher F. Baum).
If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.
If references are entirely missing, you can add them using this form.
If the full references list an item that is present in RePEc, but the system did not link to it, you can help with this form.
If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your profile, as there may be some citations waiting for confirmation.
Please note that corrections may take a couple of weeks to filter through the various RePEc services.