|
Activity Number:
|
540
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Thursday, August 2, 2007 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
ENAR
|
| Abstract - #309594 |
|
Title:
|
The Theil-Sen Estimators in Modern Regression
|
|
Author(s):
|
Hanxiang Peng*+ and Xin Dang
|
|
Companies:
|
The University of Mississippi and University of Mississippi
|
|
Address:
|
PO Box 38677, University, MS, 38677,
|
|
Keywords:
|
depth function ; efficiency ; robustness ; Theil-Sen estimator ; semiparametric regression ; Asymptotics
|
|
Abstract:
|
In this talk, we propose the use of multivariate medians to construct the Theil-Sen estimators for various regression models. We show they are robust, consistent and asymptotic normal. Simulations are conducted to compare robustness, efficiency and intensity.
|
