JSM 2005 Online Program

Abstract #303080

This is the preliminary program for the 2005 Joint Statistical Meetings in Minneapolis, Minnesota. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 7-10, 2005); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

The Program has labeled the meeting rooms with "letters" preceding the name of the room, designating in which facility the room is located:

Minneapolis Convention Center = “MCC” Hilton Minneapolis Hotel = “H” Hyatt Regency Minneapolis = “HY”

Back to main JSM 2005 Program page

Legend:

= Applied Session,

= Theme Session,

= Presenter

Activity Number:	261
Type:	Topic Contributed
Date/Time:	Tuesday, August 9, 2005 : 10:30 AM to 12:20 PM
Sponsor:	Biometrics Section
Abstract - #303080
Title:	Hybrid Methods of Inverse Regression-based Algorithms
Author(s):	Lixing Zhu*+
Companies:	The University of Hong Kong
Address:	Pokfulam Road Hong Kong, Hong Kong, 123, China
Keywords:	Sliced inverse regression ; sliced average variance estimation
Abstract:	Sliced inverse regression (SIR) and sliced average variance estimation (SAVE) are two promising methods for estimating central dimension reduction (CDR) spaces in regression models. However, SIR and SAVE have their advantages and disadvantages. SIR is insensitive to the choice of slice number, but does not work well when the regression function is symmetric or the projection direction is contained in an error term. While SAVE can handle these problems, it is less robust because it uses higher moments and is sensitive to the number of slices. Motivated by Li's (1991) ad hoc method of gaining advantages from the two methods, we develop hybrid algorithms that are convex combinations of SIR and SAVE. We prove that the space of SIR+SAVE is the direct sum of the spaces of both SIR and SAVE, and that this space is free of the coefficients in the combinations when the coefficients are not equal to either zero or one. Simulation experiments show the hybrid methods outperform both single SIR and SAVE when the coefficients are properly chosen.

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 2005 program