Title

Bayesian decision theoretic scale-adaptive estimation of a log-spectral density

Authors

Authors

M. Pensky; B. Vidakovic;D. De Canditiis

Comments

Authors: contact us about adding a copy of your work at STARS@ucf.edu

Abbreviated Journal Title

Stat. Sin.

Keywords

log-spectral density; spectral density; wavelets; WAVELET SHRINKAGE; SPLINES; Statistics & Probability

Abstract

The problem of estimating the log-spectrum of a stationary time series by Bayesian shrinkage of empirical wavelet coefficients is studied. A model in the wavelet domain that accounts for distributional properties of the log-periodogram at levels of fine detail and approximate normality at coarse levels in the wavelet decomposition, is proposed. The smoothing procedure, called BAMS-LP (Bayesian Adaptive Multiscale Shrinker of Log-Periodogram), ensures that the reconstructed log-spectrum is sufficiently noise-free. It is also shown that the resulting Bayes estimators are asymptotically optimal (in the mean-squared error sense). Comparisons with non-wavelet and wavelet-non-Bayesian methods are discussed.

Journal Title

Statistica Sinica

Volume

17

Issue/Number

2

Publication Date

1-1-2007

Document Type

Article; Proceedings Paper

Language

English

First Page

635

Last Page

666

WOS Identifier

WOS:000249307200013

ISSN

1017-0405

Share

COinS