A Generalized Block Bootstrap for Seasonal Time Series

26 Pages Posted: 7 Feb 2014

See all articles by Anna E. Dudek

Anna E. Dudek

AGH University of Science and Technology

Jacek Leśkow

Cracow University of Technology - Department of Econometrics

Efstathios Paparoditis

University of Cyprus - Department of Mathematics and Statistics

Dimitris N. Politis

University of California, San Diego (UCSD) - Department of Mathematics

Date Written: March 2014

Abstract

When time‐series data contain a periodic/seasonal component, the usual block bootstrap procedures are not directly applicable. We propose a modification of the block bootstrap – the generalized seasonal block bootstrap (GSBB) – and show its asymptotic consistency without undue restrictions on the relative size of the period and block size. Notably, it is exactly such restrictions that limit the applicability of other proposals of block bootstrap methods for time series with periodicities. The finite‐sample performance of the GSBB is also illustrated by means of a small simulation experiment.

Keywords: Periodic time series, resampling, seasonality

Suggested Citation

Dudek, Anna E. and Leśkow, Jacek and Paparoditis, Efstathios and Politis, Dimitris, A Generalized Block Bootstrap for Seasonal Time Series (March 2014). Journal of Time Series Analysis, Vol. 35, Issue 2, pp. 89-114, 2014, Available at SSRN: https://ssrn.com/abstract=2392074 or http://dx.doi.org/10.1002/jtsa.12053

Anna E. Dudek (Contact Author)

AGH University of Science and Technology

No Address Available

Jacek Leśkow

Cracow University of Technology - Department of Econometrics

Kracow
Poland

Efstathios Paparoditis

University of Cyprus - Department of Mathematics and Statistics ( email )

P.O. Box 20537
1678 Nicosia
Cyprus
00357-2-338701 (Phone)
00357-2-339061 (Fax)

Dimitris Politis

University of California, San Diego (UCSD) - Department of Mathematics ( email )

9500 Gilman Drive
La Jolla, CA 92093-0112
United States
858-534-5861 (Phone)
858-534-5273 (Fax)

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
1
Abstract Views
339
PlumX Metrics