Open Access
Translator Disclaimer
August, 1971 On the Asymptotic Optimality of Spectral Analysis for Testing Hypotheses About Time Series
W. S. Liggett Jr.
Ann. Math. Statist. 42(4): 1348-1358 (August, 1971). DOI: 10.1214/aoms/1177693247

Abstract

Classification of a sample from a zero mean, stationary, Gaussian time series into populations distinguished by characteristics of the spectrum can be done with a decision theoretic procedure or spectral analysis. Decision theory requires that each population be characterized by a probability distribution on the space of spectral density functions. In this paper, we relate the two methods by showing that under many conditions, as the sample length increases, the expected cost of the Bayes test formed from spectral estimates by approximating their sampling distribution by a product of chi-squared distributions approaches the expected cost of the Bayes test formed from the original data. The amount of smoothing that can be used in the spectral estimates depends on the prior knowledge of the order of differentiability of the spectrum. This result is related to but weaker than the notion that spectral estimates are asymptotically sufficient statistics for the second order properties of a stationary Gaussian time series.

Citation

Download Citation

W. S. Liggett Jr.. "On the Asymptotic Optimality of Spectral Analysis for Testing Hypotheses About Time Series." Ann. Math. Statist. 42 (4) 1348 - 1358, August, 1971. https://doi.org/10.1214/aoms/1177693247

Information

Published: August, 1971
First available in Project Euclid: 27 April 2007

zbMATH: 0224.62042
MathSciNet: MR293801
Digital Object Identifier: 10.1214/aoms/1177693247

Rights: Copyright © 1971 Institute of Mathematical Statistics

JOURNAL ARTICLE
11 PAGES


SHARE
Vol.42 • No. 4 • August, 1971
Back to Top