search for




 

Detection of structural changes in the covariance matrix using block wild bootstrap
Journal of the Korean Data & Information Science Society 2025;36:87-99
Published online January 31, 2025;  https://doi.org/10.7465/jkdi.2025.36.1.87
© 2025 Korean Data and Information Science Society.

Jungmin Um1 · Changryong Baek2

12Department of Statistics, Sungkyunkwan University, Seoul, Korea
Correspondence to: This work was supported by the Basic Science Research Program from the National Research Foundation of Korea (NRF-2022R1F1A1066209).
1 Graduate student, Department of Statistics, Sungkyunkwan University, Seoul 03063, Korea.
2 Corresponding author: Professor, Department of Statistics, Sungkyunkwan University, Seoul 03063, Korea. E-mail: crbaek@skku.edu
Received September 24, 2024; Revised October 6, 2024; Accepted October 6, 2024.
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
This paper aims to improve the limitations of the CUSUM-based method for detecting structural changes in covariance matrices proposed by Aue et al. (2009). These limitations arise from difficulties in long-run variance estimation, which worsen as correlations increase, leading to size distortions in finite samples. To address these challenges, the study adopts a block wild bootstrap technique. Simulations show that this approach effectively reduces size distortions in finite samples. Specifically, when the block size is selected in a data-adaptive manner, the empirical size closely matches the target significance level. In the empirical analysis, 15 major sectors in South Korea over the past six years were analyzed, and changes reflecting major economic events were detected.
Keywords : Block wild bootstrap, change point, CUSUM, high-dimensional, volatility