|
Activity Number:
|
101
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 4, 2008 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistical Computing
|
| Abstract - #301961 |
|
Title:
|
Nonparametric Density Deconvolution by Weighted Kernel Estimators
|
|
Author(s):
|
Berwin A. Turlach*+ and Martin L. Hazelton
|
|
Companies:
|
National University of Singapore and Massey University
|
|
Address:
|
Dept of Statistics and Appl Prob, Singapore, 117546, Singapore
|
|
Keywords:
|
Density estimation ; Errors in variables ; Integrated square error ; Measurement error ; Weights
|
|
Abstract:
|
Nonparametric density estimation in the presence of measurement error is considered. In this paper a new approach based on a weighted kernel density estimator is proposed as opposed to the usual kernel deconvolution estimator which uses a modified kernel. In practice a data driven method of weight selection is required. Our strategy is to minimize the discrepancy between a standard kernel estimate from the contaminated data on the one hand, and the convolution of the weighted deconvolution estimate with the measurement error density on the other hand. We consider a direct implementation of this approach, in which the weights are optimized subject to sum and non-negativity constraints, and a regularized version in which the objective function includes a ridge-type penalty. Numerical tests suggest that the weighted kernel estimation can lead to tangible improvements.
|
