MODELLING HIGH RISK SCENARIOS WITH GAUGE FUNCTIONS CONSTRUCTED FROM GUMBEL COPULAS AND $D$-VINE STRUCTURES
Far East Journal of Theoretical Statistics · 12.08.2026 · 70 (3) · 401-437
DOI: 10.17654/0972086326019 ↗Kurz gefasst
Fachartikel in der Zeitschrift Far East Journal of Theoretical Statistics, online erschienen am 12.08.2026. Verfasst von Souleymane Ouédraogo und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The gauge function plays a crucial role in modelling the dependence structure of multivariate extremes within the framework of the geometric approach. This approach involves rescaling the data so that they converge toward an extreme region, characterized by a function known as the gauge function. It provides a link between the domain defined by this function and the dependence structure of the extreme values observed within that domain. Several recent studies have aimed to enhance this framework, whose flexibility lies in the appropriate specification of the gauge function. Our research follows this line of development by proposing, in addition to those already available in the literature, new forms of gauge functions. Specifically, we introduce two new gauge functions derived from both $D$-vine density decompositions and the Gumbel copula, the latter being particularly well-suited for modelling multivariate extreme dependence. These functions are built upon third-order $D$-vine decompositions and incorporate the Gumbel copula to better capture the tail relationships between variables. The proposed gauge functions are illustrated through a practical application involving the evaluation and fitting of the geometric model to estimate small probabilities associated with occurrences in extreme or high-risk regions. Finally, a real-data application is presented to assess the ability of our proposed functions to capture dependence in the extreme tails.
Zitieren
APA
Ouédraogo, S., & Bagré, R. G. (2026). MODELLING HIGH RISK SCENARIOS WITH GAUGE FUNCTIONS CONSTRUCTED FROM GUMBEL COPULAS AND $D$-VINE STRUCTURES. Far East Journal of Theoretical Statistics, 70(3), 401-437. https://doi.org/10.17654/0972086326019
Vancouver
Ouédraogo S, Bagré RG. MODELLING HIGH RISK SCENARIOS WITH GAUGE FUNCTIONS CONSTRUCTED FROM GUMBEL COPULAS AND $D$-VINE STRUCTURES. Far East Journal of Theoretical Statistics. 2026;70(3):401-437. doi:10.17654/0972086326019
BibTeX
@article{Oudraogo2026,
author = {Ouédraogo, Souleymane and Bagré, Remi Guillaume},
title = {MODELLING HIGH RISK SCENARIOS WITH GAUGE FUNCTIONS CONSTRUCTED FROM GUMBEL COPULAS AND $D$-VINE STRUCTURES},
journal = {Far East Journal of Theoretical Statistics},
year = {2026},
volume = {70},
number = {3},
pages = {401--437},
doi = {10.17654/0972086326019}
}
EUVIMED