Identification of distributional heterogeneity under maximum adjacent separation subspace

Luoyao Yu () and Xuehu Zhu ()
Additional contact information
Luoyao Yu: Xi’an Jiaotong University
Xuehu Zhu: Xi’an Jiaotong University

Statistical Papers, 2025, vol. 66, issue 6, No 13, 33 pages

Abstract: Abstract This study develops a novel dimension reduction strategy to enhance distributional change point detection, which addresses the curse of dimensionality for some popular nonparametric change point detection methods. Firstly, based on the squared Hellinger distance, we propose the maximum adjacent separation subspace (MASS), which preserves the integrity of the change point information. Recognizing the challenge of identifying precise change point locations beforehand, we further present an exhaustive estimator of MASS based on a segmentation method. This estimator retains key change point information after dimension reduction and eliminates the need to identify exact change point locations. Additionally, we present its asymptotic property. Finally, we obtain the estimator by using the Riemannian Manifold Optimization method and apply a classical nonparametric change point detection to the lower dimensional data. Through several simulations and applications to real data, we demonstrate that the dimension reduction strategy enhances the performance of nonparametric change point detection methods in finite sample scenarios.

Keywords: Dimension reduction; Maximum adjacent separation subspace; Hellinger distance; Change points (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s00362-025-01760-4 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:stpapr:v:66:y:2025:i:6:d:10.1007_s00362-025-01760-4

Ordering information: This journal article can be ordered from
http://www.springer. ... business/journal/362

DOI: 10.1007/s00362-025-01760-4

Access Statistics for this article

Statistical Papers is currently edited by C. Müller, W. Krämer and W.G. Müller

More articles in Statistical Papers from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().