This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.

Abstract Details

Activity Number: 682
Type: Contributed
Date/Time: Thursday, August 5, 2010 : 10:30 AM to 12:20 PM
Sponsor: Section on Statistical Graphics
Abstract - #306559
Title: An Application of Location-Dispersion Orthogonality in Quadratic Discriminant Analysis
Author(s): Santiago Velilla*+
Companies: Universidad Carlos III de Madrid
Address: UNIVERSIDAD CARLOS III DE MADRID, GETAFE (MADRID), International, 28903, SPAIN
Keywords: Data representation ; Dimension reduction suspaces ; Reduced quadratic discrimination ; SAVE ; SIR ; SIRII
Abstract:

Dimension reduction in quadratic discriminant analysis has not received, so far, a universally accepted solution in the literature. Directions associated to several proposed kernel matrices are, typically, non interpretable, since they do not distinguish clearly between the location and dispersion separation. However, as it is commonly found in practice, the differences between the class mean vectors and covariance matrices can be usually explained by a population model in which the location and dispersion subspaces are perpendicular. An application of these ideas is presented in connection with the Swiss bank notes data of Flury and Riedwyl (1988).


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 2010 program




2010 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.