2019
DOI: 10.1007/s11222-019-09878-w
|View full text |Cite
|
Sign up to set email alerts
|

Semiparametric bivariate modelling with flexible extremal dependence

Abstract: Inference over multivariate tails often requires a number of assumptions which may affect the assessment of the extreme dependence structure. Models are usually constructed in such a way that extreme components can either be asymptotically dependent or be independent of each other. Recently, there has been an increasing interest on modelling multivariate extremes more flexibly, by allowing models to bridge both asymptotic dependence regimes. Here we propose a novel semiparametric approach which allows for a va… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2

Citation Types

0
2
0

Year Published

2021
2021
2022
2022

Publication Types

Select...
3

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(2 citation statements)
references
References 58 publications
0
2
0
Order By: Relevance
“…Our approach shares similarities with spliced models (see, e.g,. Reynkens et al, 2017; Castro‐Camilo et al, 2019; Opitz et al, 2018) and mixture models for extremes (Behrens et al, 2004; Carreau & Bengio, 2009; de Melo Mendes & Lopes, 2004; Do Nascimento et al, 2011; Frigessi et al, 2002; Leonelli & Gamerman, 2020) in the sense that all of these methods join two distributions. But besides this, our approach is fundamentally different from that of spliced or mixture models.…”
Section: Introductionmentioning
confidence: 99%
“…Our approach shares similarities with spliced models (see, e.g,. Reynkens et al, 2017; Castro‐Camilo et al, 2019; Opitz et al, 2018) and mixture models for extremes (Behrens et al, 2004; Carreau & Bengio, 2009; de Melo Mendes & Lopes, 2004; Do Nascimento et al, 2011; Frigessi et al, 2002; Leonelli & Gamerman, 2020) in the sense that all of these methods join two distributions. But besides this, our approach is fundamentally different from that of spliced or mixture models.…”
Section: Introductionmentioning
confidence: 99%
“…To make inference, we propose and compare a full likelihood and various censored likelihood approaches, exploring three different censoring schemes that are specifically designed to prioritize model calibration in the lower and upper-tail regions while downweighting the contribution of nonextreme observations in the bulk. In particular, our full-likelihood approach is similar to other papers that study extremes and assess the joint-tail risk using the complete dataset (Aulbach, Bayer and Falk (2012), Hazra, Reich and Staicu (2020), Leonelli and Gamerman (2020), Vrac, Naveau and Drobinski (2007)). Furthermore, we also develop a (weighted) local likelihood approach that can capture complex time-varying dependence behaviors, to uncover how the extremal dependence among any two leading cryptocurrencies has evolved over time.…”
Section: Introductionmentioning
confidence: 99%