The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Online Program Home
Abstract Details
|
Activity Number:
|
444
|
|
Type:
|
Invited
|
|
Date/Time:
|
Wednesday, August 1, 2012 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
IMS
|
| Abstract - #303879 |
|
Title:
|
Assessing the Impacts of Interactions of Feature Selection
|
|
Author(s):
|
Peter Hall*+ and Jinghao Xue
|
|
Companies:
|
University of Melbourne and University College London
|
|
Address:
|
Department of Mathematics and Statistics, The University of Melbourne, , Australia
|
|
Keywords:
|
Bootstrap ;
Classification ;
Feature selection ;
High dimension
|
|
Abstract:
|
Many feature selection methods involve assessing features individually. In this talk we present a technique which, without requiring computational resources that are much more than those needed for feature-wise analysis, allows identification of interactions. In particular it enables access to features whose importance is expressed predominantly through their interactions with one or more other features, rather than when acting alone. The approach is recursive, and works by, first, detecting a slight trace of an interacting feature as a univariate quantity, and then exploring that further.
|
The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.
Back to the full JSM 2012 program
|
2012 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Continuing Education program, please contact the Education Department.