Real-time changepoint detection in a nonlinear expectile model

Gabriela Ciuperca (), Matúš Maciak () and Michal Pešta ()
Additional contact information
Gabriela Ciuperca: Université Lyon 1
Matúš Maciak: Charles University
Michal Pešta: Charles University

Metrika: International Journal for Theoretical and Applied Statistics, 2024, vol. 87, issue 2, No 1, 105-131

Abstract: Abstract An online changepoint detection procedure based on conditional expectiles is introduced. The key contribution is threefold: nonlinearity of the underlying model improves the overall flexibility while a parametric form of the unknown regression function preserves a simple and straightforward interpretation; The conditional expectiles, well-known in econometrics for being the only coherent and elicitable risk measure, introduce additional robustness—especially with respect to asymmetric error distributions common in various types of data; The proposed statistical test is proved to be consistent and the distribution under the null hypothesis does not depend on the functional form of the underlying model nor the unknown parameters. Empirical properties of the proposed real-time changepoint detection test are investigated in a simulation study and a practical applicability is illustrated using the Covid-19 prevalence data from Prague.

Keywords: Asymmetric least squares; Changepoint test; Conditional expectiles; Online detection; Coherent risk measure (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s00184-023-00904-6 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:metrik:v:87:y:2024:i:2:d:10.1007_s00184-023-00904-6

Ordering information: This journal article can be ordered from
http://www.springer.com/statistics/journal/184/PS2

DOI: 10.1007/s00184-023-00904-6

Access Statistics for this article

Metrika: International Journal for Theoretical and Applied Statistics is currently edited by U. Kamps and Norbert Henze

More articles in Metrika: International Journal for Theoretical and Applied Statistics from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().