American Statistical Association
New York City
Metropolitan Area Chapter

Mailman School of Public Health
Columbia University
Department of Biostatistics Colloquium



DIMENSION REDUCTION BASED ON
CONSTRAINED CANONICAL CORRELATION
AND VARIABLE FILTERING

by

Prof. Jianhui Zhou
Department of Statistics
University of Virginia


Abstract

The “curse of dimensionality” has remained a challenge for high-dimensional data analysis in statistics. The canonical correlation (CANCOR) method aims to reduce the dimensionality of data by replacing the explanatory variables with a small number of composite directions without losing much information. However, the estimated composite directions by CANCOR generally involve all of the variables, making their interpretation difficult. To simplify the direction estimates, we propose the constrained canonical correlation method based on CANCOR, followed by a simple variable filtering method. As a result, each estimated composite direction consists of a subset of the variables for interpretability as well as predictive power. The proposed method aims to identify simple structures without sacrificing the desirable properties of the unconstrained CANCOR estimates. The simulation studies demonstrate the performance advantage of the proposed method over the existing ones. The proposed method is also applied to two examples for illustration.


Date: Thursday, March 27, 2008
Time: 4:00 - 5:00 P.M.
Location: Mailman School of Public Health
Department of Biostatistics
722 West 168th Street
Judith Jansen Conference Room
4th Floor - Room 425
New York, New York

RESERVATIONS ARE NOT REQUIRED

Refreshments will be served at 3:30 P.M. in the
Biostatistics Conference Room (R627).


Home Page | Chapter News | Chapter Officers | Chapter Events
Other Metro Area Events | ASA National Home Page | Links To Other Websites

Copyright © 2008 by New York City Metropolitan Area Chapter of the ASA
Designed and maintained by Cynthia Scherer
Send questions or comments to nycasa@mindspring.com