Open Access
Translator Disclaimer
February 2012 Covariance matrix estimation for stationary time series
Han Xiao, Wei Biao Wu
Ann. Statist. 40(1): 466-493 (February 2012). DOI: 10.1214/11-AOS967

Abstract

We obtain a sharp convergence rate for banded covariance matrix estimates of stationary processes. A precise order of magnitude is derived for spectral radius of sample covariance matrices. We also consider a thresholded covariance matrix estimator that can better characterize sparsity if the true covariance matrix is sparse. As our main tool, we implement Toeplitz [Math. Ann. 70 (1911) 351–376] idea and relate eigenvalues of covariance matrices to the spectral densities or Fourier transforms of the covariances. We develop a large deviation result for quadratic forms of stationary processes using m-dependence approximation, under the framework of causal representation and physical dependence measures.

Citation

Download Citation

Han Xiao. Wei Biao Wu. "Covariance matrix estimation for stationary time series." Ann. Statist. 40 (1) 466 - 493, February 2012. https://doi.org/10.1214/11-AOS967

Information

Published: February 2012
First available in Project Euclid: 16 April 2012

zbMATH: 1246.62191
MathSciNet: MR3014314
Digital Object Identifier: 10.1214/11-AOS967

Subjects:
Primary: 62M10
Secondary: 62H12

Keywords: Autocovariance matrix , banding , large deviation , physical dependence measure , short range dependence , Spectral density , stationary process , tapering , thresholding , Toeplitz matrix

Rights: Copyright © 2012 Institute of Mathematical Statistics

JOURNAL ARTICLE
28 PAGES


SHARE
Vol.40 • No. 1 • February 2012
Back to Top