Abstract Details
Activity Number:
|
39
|
Type:
|
Contributed
|
Date/Time:
|
Sunday, August 3, 2014 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Section on Statistical Learning and Data Mining
|
Abstract #312345
|
View Presentation
|
Title:
|
Sequential Partial Inverse Regression
|
Author(s):
|
Haileab Hilafu*+ and Xiangrong Yin
|
Companies:
|
University of Georgia and University of Georgia
|
Keywords:
|
Sufficient Dimension Reduction ;
Central Subspace ;
Partial Least Squares
|
Abstract:
|
Sufficient Dimension Reduction (SDR) is a dimension reduction paradigm for reducing the dimension of the predictor vector without losing regression information. Classical SDR methods require inverting the predictor covariance matrix. This has hindered the use of these methods in cases where the dimension of the predictor vector exceeds the available sample size. Li, Cook and Tsai (2007) adopted the idea of partial least squares (PLS) estimation to avoid inverting the covariance matrix and proposed 'partial inverse regression' by restricting to the case where the structural dimension is one. This was further developed to handle cases where the structural dimension exceeds one by Cook, Li and Chiaromonte (2007). In this talk, we will present a sequential approach to extend the scope of these methodologies to the high-dimensional setting. The efficacy of the method is demonstrated through extensive simulation and application to real data.
|
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.