Abstract Details
Activity Number:
|
508
|
Type:
|
Contributed
|
Date/Time:
|
Wednesday, August 6, 2014 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Statistical Computing
|
Abstract #313354
|
View Presentation
|
Title:
|
Computational Procedure for L1-Based Principal Components
|
Author(s):
|
Robert Pavur*+ and Constantine Loucopoulos and Kellie Keeling
|
Companies:
|
University of North Texas and Northeastern Ilinois University and University of Denver
|
Keywords:
|
Principal Components ;
L1 norm ;
mathematical programming
|
Abstract:
|
Mathematical programming approaches have been used in classification problems as an alternative to discriminant analysis. The approach in this presentation is to illustrate a mathematical programming approach to obtaining a principal component that may be more robust to outliers and skewed data. This approach is based on the L1 norm concept and has similarities to alternative mathematical programming approaches in discriminant analysis. This approach also allows for the successive mathematical programming principal components to be correlated. A simulation study compares results from L2 based principal components and L1 based principal components.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2014 program
|
2014 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Professional Development program, please contact the Education Department.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Copyright © American Statistical Association.