Integer-Valued Designs and Wavelet Versions
Of Nonparametric Curve Estimators
by Alwell J. Oyet and Li Mei Sun
.
Abstract:
Wavelet versions of nonparametric curve estimators
and weighted least squares wavelet regression are discussed.
We introduce a modified version of the Gasser-Muller estimator.
We use the modified version to construct integer-valued designs
for nonparametric curve estimation using the simulated annealing
algorithm. Our examples involve the Haar, Daubechies and multiwavelet
systems.
Key Words:
Daubechies Wavelet; Gasser-Muller Estimator; Simulated
Annealing; Thresholding
Authors:
Alwell J. Oyet,
aoyet@math.mun.ca
Mei Sun,
limei@math.mun.ca
Editor:
Wei-Min Huang
,
wh02@lehigh.edu
READING THE ARTICLE: You can read the article in
portable document (.pdf) format (2451406 bytes.)
NOTE: The content of this article is the intellectual property of the authors, who retains all rights to future publication.
This page has been accessed 256 times since July 24, 2006.
Return to the 
Home Page.