|
Activity Number:
|
159
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Monday, August 3, 2009 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Nonparametric Statistics
|
| Abstract - #303279 |
|
Title:
|
New Robust Statistical Procedures for Semiparametric Regression Models
|
|
Author(s):
|
Bo Kai*+ and Runze Li and Hui Zou
|
|
Companies:
|
Penn State University and Penn State University and University of Minnesota
|
|
Address:
|
326 Thomas Building, University Park, PA, 16802-2111,
|
|
Keywords:
|
semiparametric model ; quantile regression ; composite quantile regression ; variable selection ; oracle property
|
|
Abstract:
|
The complexity of semiparametric models poses new challenges to parametric inferences and model selection that frequently arise from real applications. In this work, we propose new robust inference procedures for semiparametric varying-coefficient models. We first study quantile regression estimate for the nonparametric varying-coefficient functions and the parametric regression coefficients. To improve efficiency, we develop composite quantile regression procedure for both components. To achieve sparsity, we further develop a variable selection procedure. We study the sampling property of the resulting estimates. With proper choices of penalty functions and regularization parameters, we show the proposed variable selection procedure possesses the oracle property. Extensive Monte Carlo simulation studies are conducted to examine the finite sample performance of the proposed procedures.
|
