Home > Research > Publications & Outputs > Modelling across extremal dependence classes

Electronic data

  • WTDE_dependence_final

    Rights statement: This is the peer reviewed version of the following article: Wadsworth, J. L., Tawn, J. A., Davison, A. C. and Elton, D. M. (2017), Modelling across extremal dependence classes. J. R. Stat. Soc. B, 79: 149–175. doi:10.1111/rssb.12157 which has been published in final form at http://onlinelibrary.wiley.com/doi/10.1111/rssb.12157/abstract This article may be used for non-commercial purposes in accordance With Wiley Terms and Conditions for self-archiving.

    Accepted author manuscript, 596 KB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

  • SuppMat_round3

    Rights statement: This is the peer reviewed version of the following article: Wadsworth, J. L., Tawn, J. A., Davison, A. C. and Elton, D. M. (2017), Modelling across extremal dependence classes. J. R. Stat. Soc. B, 79: 149–175. doi:10.1111/rssb.12157 which has been published in final form at http://onlinelibrary.wiley.com/doi/10.1111/rssb.12157/abstract This article may be used for non-commercial purposes in accordance With Wiley Terms and Conditions for self-archiving.

    Accepted author manuscript, 249 KB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

Modelling across extremal dependence classes

Research output: Contribution to journalJournal article

Published

Standard

Modelling across extremal dependence classes. / Wadsworth, Jenny; Tawn, Jonathan Angus; Davison, Anthony; Elton, Daniel Mark.

In: Journal of the Royal Statistical Society: Series B (Statistical Methodology), Vol. 79, No. 1, 01.2017, p. 149-175.

Research output: Contribution to journalJournal article

Harvard

Wadsworth, J, Tawn, JA, Davison, A & Elton, DM 2017, 'Modelling across extremal dependence classes', Journal of the Royal Statistical Society: Series B (Statistical Methodology), vol. 79, no. 1, pp. 149-175. https://doi.org/10.1111/rssb.12157

APA

Wadsworth, J., Tawn, J. A., Davison, A., & Elton, D. M. (2017). Modelling across extremal dependence classes. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 79(1), 149-175. https://doi.org/10.1111/rssb.12157

Vancouver

Wadsworth J, Tawn JA, Davison A, Elton DM. Modelling across extremal dependence classes. Journal of the Royal Statistical Society: Series B (Statistical Methodology). 2017 Jan;79(1):149-175. https://doi.org/10.1111/rssb.12157

Author

Wadsworth, Jenny ; Tawn, Jonathan Angus ; Davison, Anthony ; Elton, Daniel Mark. / Modelling across extremal dependence classes. In: Journal of the Royal Statistical Society: Series B (Statistical Methodology). 2017 ; Vol. 79, No. 1. pp. 149-175.

Bibtex

@article{c3f266c9e9f9438ea68a7ee0ae916d2c,
title = "Modelling across extremal dependence classes",
abstract = "Different dependence scenarios can arise in multivariate extremes, entailing careful selection of an appropriate class of models. In bivariate extremes, the variables are either asymptotically dependent or are asymptotically independent. Most available statistical models suit one or other of these cases, but not both, resulting in a stage in the inference that is unaccounted for, but can substantially impact subsequent extrapolation. Existing modelling solutions to this problem are either applicable only on sub-domains, or appeal to multiple limit theories. We introduce a unified representation for bivariate extremes that encompasses a wide variety of dependence scenarios, and applies when at least one variable is large. Our representation motivates a parametric model that encompasses both dependence classes. We implement a simple version of this model, and show that it performs well in a range of settings.",
keywords = "asymptotic independence, censored likelihood, conditional extremes, dependence modelling, extreme value theory, multivariate regular variation",
author = "Jenny Wadsworth and Tawn, {Jonathan Angus} and Anthony Davison and Elton, {Daniel Mark}",
note = "This is the peer reviewed version of the following article: Wadsworth, J. L., Tawn, J. A., Davison, A. C. and Elton, D. M. (2017), Modelling across extremal dependence classes. J. R. Stat. Soc. B, 79: 149–175. doi:10.1111/rssb.12157 which has been published in final form at http://onlinelibrary.wiley.com/doi/10.1111/rssb.12157/abstract This article may be used for non-commercial purposes in accordance With Wiley Terms and Conditions for self-archiving.",
year = "2017",
month = "1",
doi = "10.1111/rssb.12157",
language = "English",
volume = "79",
pages = "149--175",
journal = "Journal of the Royal Statistical Society: Series B (Statistical Methodology)",
issn = "1369-7412",
publisher = "Wiley-Blackwell",
number = "1",

}

RIS

TY - JOUR

T1 - Modelling across extremal dependence classes

AU - Wadsworth, Jenny

AU - Tawn, Jonathan Angus

AU - Davison, Anthony

AU - Elton, Daniel Mark

N1 - This is the peer reviewed version of the following article: Wadsworth, J. L., Tawn, J. A., Davison, A. C. and Elton, D. M. (2017), Modelling across extremal dependence classes. J. R. Stat. Soc. B, 79: 149–175. doi:10.1111/rssb.12157 which has been published in final form at http://onlinelibrary.wiley.com/doi/10.1111/rssb.12157/abstract This article may be used for non-commercial purposes in accordance With Wiley Terms and Conditions for self-archiving.

PY - 2017/1

Y1 - 2017/1

N2 - Different dependence scenarios can arise in multivariate extremes, entailing careful selection of an appropriate class of models. In bivariate extremes, the variables are either asymptotically dependent or are asymptotically independent. Most available statistical models suit one or other of these cases, but not both, resulting in a stage in the inference that is unaccounted for, but can substantially impact subsequent extrapolation. Existing modelling solutions to this problem are either applicable only on sub-domains, or appeal to multiple limit theories. We introduce a unified representation for bivariate extremes that encompasses a wide variety of dependence scenarios, and applies when at least one variable is large. Our representation motivates a parametric model that encompasses both dependence classes. We implement a simple version of this model, and show that it performs well in a range of settings.

AB - Different dependence scenarios can arise in multivariate extremes, entailing careful selection of an appropriate class of models. In bivariate extremes, the variables are either asymptotically dependent or are asymptotically independent. Most available statistical models suit one or other of these cases, but not both, resulting in a stage in the inference that is unaccounted for, but can substantially impact subsequent extrapolation. Existing modelling solutions to this problem are either applicable only on sub-domains, or appeal to multiple limit theories. We introduce a unified representation for bivariate extremes that encompasses a wide variety of dependence scenarios, and applies when at least one variable is large. Our representation motivates a parametric model that encompasses both dependence classes. We implement a simple version of this model, and show that it performs well in a range of settings.

KW - asymptotic independence

KW - censored likelihood

KW - conditional extremes

KW - dependence modelling

KW - extreme value theory

KW - multivariate regular variation

U2 - 10.1111/rssb.12157

DO - 10.1111/rssb.12157

M3 - Journal article

VL - 79

SP - 149

EP - 175

JO - Journal of the Royal Statistical Society: Series B (Statistical Methodology)

JF - Journal of the Royal Statistical Society: Series B (Statistical Methodology)

SN - 1369-7412

IS - 1

ER -