Cookies?
Library Header Image
LSE Research Online LSE Library Services

Identifying the finite dimensionality of curve time series

Bathia, Neil, Yao, Qiwei and Ziegelmann, Flavio (2010) Identifying the finite dimensionality of curve time series. The Annals of Statistics, 38 (6). pp. 3352-3386. ISSN 0090-5364

[img]
Preview
PDF
Download (853Kb) | Preview

Abstract

The curve time series framework provides a convenient vehicle to accommodate some nonstationary features into a stationary setup. We propose a new method to identify the dimensionality of curve time series based on the dynamical dependence across different curves. The practical implementation of our method boils down to an eigenanalysis of a finite-dimensional matrix. Furthermore, the determination of the dimensionality is equivalent to the identification of the nonzero eigenvalues of the matrix, which we carry out in terms of some bootstrap tests. Asymptotic properties of the proposed method are investigated. In particular, our estimators for zero-eigenvalues enjoy the fast convergence rate n while the estimators for nonzero eigenvalues converge at the standard √n-rate. The proposed methodology is illustrated with both simulated and real data sets.

Item Type: Article
Official URL: http://www.imstat.org/aos/
Additional Information: © 2010 Institute of Mathematical Statistics
Library of Congress subject classification: Q Science > QA Mathematics
Sets: Departments > Statistics
Rights: http://www.lse.ac.uk/library/usingTheLibrary/academicSupport/OA/depositYourResearch.aspx
Identification Number: UT ISI:000290231500001
Date Deposited: 26 Jan 2011 09:48
URL: http://eprints.lse.ac.uk/31709/

Actions (login required)

Record administration - authorised staff only Record administration - authorised staff only