|
Activity Number:
|
142
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 7, 2006 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Nonparametric Statistics
|
| Abstract - #306906 |
|
Title:
|
Boundary Kernel Method in Nonparametric Deconvolution
|
|
Author(s):
|
Shunpu Zhang*+
|
|
Companies:
|
University of Nebraska-Lincoln
|
|
Address:
|
340 Hardin Hall, N., Lincoln, NE, 68583,
|
|
Keywords:
|
deconvolution ; boundary kernel estimator ; density estimation ; boundary effect
|
|
Abstract:
|
This paper considers nonparametric deconvolution problem when the true density function is truncated. We propose to use the deconvolution boundary kernel method to remove the boundary effect of the conventional deconvolution density estimator. Methods of constructing deconvolution boundary kernels are provided. The mean square error properties, including the rates of convergence, are investigated for supersmooth and ordinary smooth errors. It is shown that the deconvolution boundary kernel estimator successfully removes the boundary effects of the conventional deconvolution density estimator. Simulations are carried out to compare the performance of the deconvolution boundary kernel estimator and the conventional deconvolution estimator.
|
