| | |
Summary: Computational Statistics & Data Analysis 39 (2002) 435451
www.elsevier.com/locate/csda
Empirical Bayes approach to block
wavelet function estimation
Felix Abramovicha, Panagiotis Besbeasb, Theofanis Sapatinasc;
a
Department of Statistics and Operations Research, Tel Aviv University, Ramat Aviv 69978, Israel
b
Institute of Mathematics and Statistics, University of Kent at Canterbury, Vent CT2 7 NF, UK
c
Department of Mathematics and Statistics, University of Cyprus, P.O. Box 20537,
Nicosia CY 1678, Cyprus
Received 1 December 2000
Abstract
Wavelet methods have demonstrated considerable success in function estimation through term-by-term
thresholding of the empirical wavelet coe cients. However, it has been shown that grouping the em-
pirical wavelet coe cients into blocks and making simultaneous threshold decisions about all the co-
e cients in each block has a number of advantages over term-by-term wavelet thresholding, including
asymptotic optimality and better mean squared error performance in ˙nite sample situations. An empir-
ical Bayes approach to incorporating information on neighbouring empirical wavelet coe cients into
|
