search for




 

Bootstrap methods for detecting parameter change in count time series
Journal of the Korean Data & Information Science Society 2025;36:153-62
Published online January 31, 2025;  https://doi.org/10.7465/jkdi.2025.36.1.153
© 2025 Korean Data and Information Science Society.

Jiwon Kang1

1Department of Data Science, Jeju National University
Correspondence to: 1 Associate professor, Department of Data Science, Jeju National University, Jeju 63243, Korea. E-mail: jwkang@jejunu.ac.kr
Received December 29, 2024; Revised January 12, 2025; Accepted January 12, 2025.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
In this paper, we propose a bootstrap method for testing parameter change in Poisson autoregressive (AR) models. First, we review the estimates-based and the residualbased cumulative sum (CUSUM) tests in Poisson AR models. To address size distortions and enhance the performance of the CUSUM tests in small-sample scenarios, we introduce bootstrap versions of these two types of CUSUM tests. Simulation results demonstrate the validity of the proposed bootstrap tests. Furthermore, the proposed methodology is applied to two real datasets for illustration.
Keywords : Bootstrap methods, campylobacteriosis infections data, change point detection, poisson autoregressive models, polio incidence data