Using B-splines for nonparametric inference on bivariate extreme-value copulas

Eric Cormier; Christian Genest; Johanna G. Nešlehová

doi:10.1007/s10687-014-0199-4

Using B-splines for nonparametric inference on bivariate extreme-value copulas

Eric Cormier, Christian Genest^*, Johanna G. Nešlehová

^*Korrespondierende*r Autor*in für diese Arbeit

Publikation: Wissenschaftliche Fachzeitschrift › Originalbeitrag in Fachzeitschrift › Begutachtung

Abstract

A visual tool is proposed for detecting the presence of extreme-value dependence or extremal tail behavior in bivariate data. The points appearing on the plot stem from rank-based transformations of the observations and can serve to estimate the unknown Pickands dependence function of the underlying extreme-value copula or its attractor. Quadratic constrained B-spline smoothing is used to derive an intrinsic estimator, which naturally leads to a test of extremeness. Both the estimator and the test are seen to perform well in simulations. The proposed methodology is illustrated with real data and the treatment of ties is briefly discussed.

Originalsprache	Englisch
Seiten (von - bis)	633-659
Seitenumfang	27
Fachzeitschrift	Extremes
Jahrgang	17
Ausgabenummer	4
DOIs	https://doi.org/10.1007/s10687-014-0199-4
Publikationsstatus	Veröffentlicht - 27 Nov. 2014
Extern publiziert	Ja

Bibliographische Notiz

Funding Information:
Acknowledgements Funding for this work was provided by the Canada Research Chairs Program, the Natural Sciences and Engineering Research Council of Canada, the Canadian Statistical Sciences Institute, and the Fonds de recherche du Québec – Nature et technologies.

Publisher Copyright:
© 2014, Springer Science+Business Media New York.

Zugriff auf Dokument

10.1007/s10687-014-0199-4

Verfügbarkeit prüfen

Katalog der Universitätsbibliothek

Zitat

@article{aa30afd02cef4578bb704b1d37afabff,

title = "Using B-splines for nonparametric inference on bivariate extreme-value copulas",

abstract = "A visual tool is proposed for detecting the presence of extreme-value dependence or extremal tail behavior in bivariate data. The points appearing on the plot stem from rank-based transformations of the observations and can serve to estimate the unknown Pickands dependence function of the underlying extreme-value copula or its attractor. Quadratic constrained B-spline smoothing is used to derive an intrinsic estimator, which naturally leads to a test of extremeness. Both the estimator and the test are seen to perform well in simulations. The proposed methodology is illustrated with real data and the treatment of ties is briefly discussed.",

keywords = "B-spline, Copula, Extreme-value, Pickands dependence function",

author = "Eric Cormier and Christian Genest and Ne{\v s}lehov{\'a}, {Johanna G.}",

note = "Publisher Copyright: {\textcopyright} 2014, Springer Science+Business Media New York.",

year = "2014",

month = nov,

day = "27",

doi = "10.1007/s10687-014-0199-4",

language = "English",

volume = "17",

pages = "633--659",

journal = "Extremes",

issn = "1386-1999",

publisher = "Springer Netherlands",

number = "4",

}

TY - JOUR

T1 - Using B-splines for nonparametric inference on bivariate extreme-value copulas

AU - Cormier, Eric

AU - Genest, Christian

AU - Nešlehová, Johanna G.

PY - 2014/11/27

Y1 - 2014/11/27

N2 - A visual tool is proposed for detecting the presence of extreme-value dependence or extremal tail behavior in bivariate data. The points appearing on the plot stem from rank-based transformations of the observations and can serve to estimate the unknown Pickands dependence function of the underlying extreme-value copula or its attractor. Quadratic constrained B-spline smoothing is used to derive an intrinsic estimator, which naturally leads to a test of extremeness. Both the estimator and the test are seen to perform well in simulations. The proposed methodology is illustrated with real data and the treatment of ties is briefly discussed.

AB - A visual tool is proposed for detecting the presence of extreme-value dependence or extremal tail behavior in bivariate data. The points appearing on the plot stem from rank-based transformations of the observations and can serve to estimate the unknown Pickands dependence function of the underlying extreme-value copula or its attractor. Quadratic constrained B-spline smoothing is used to derive an intrinsic estimator, which naturally leads to a test of extremeness. Both the estimator and the test are seen to perform well in simulations. The proposed methodology is illustrated with real data and the treatment of ties is briefly discussed.

KW - B-spline

KW - Copula

KW - Extreme-value

KW - Pickands dependence function

U2 - 10.1007/s10687-014-0199-4

DO - 10.1007/s10687-014-0199-4

M3 - Journal article

AN - SCOPUS:84912103010

SN - 1386-1999

VL - 17

SP - 633

EP - 659

JO - Extremes

JF - Extremes

IS - 4

ER -