Likelihood estimators for multivariate extremes

Handle URI:
http://hdl.handle.net/10754/583987
Title:
Likelihood estimators for multivariate extremes
Authors:
Huser, Raphaël ( 0000-0002-1228-2071 ) ; Davison, Anthony C.; Genton, Marc G. ( 0000-0001-6467-2998 )
Abstract:
The main approach to inference for multivariate extremes consists in approximating the joint upper tail of the observations by a parametric family arising in the limit for extreme events. The latter may be expressed in terms of componentwise maxima, high threshold exceedances or point processes, yielding different but related asymptotic characterizations and estimators. The present paper clarifies the connections between the main likelihood estimators, and assesses their practical performance. We investigate their ability to estimate the extremal dependence structure and to predict future extremes, using exact calculations and simulation, in the case of the logistic model.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Citation:
Likelihood estimators for multivariate extremes 2015 Extremes
Publisher:
Springer Science + Business Media
Journal:
Extremes
Issue Date:
17-Nov-2015
DOI:
10.1007/s10687-015-0230-4
Type:
Article
ISSN:
1386-1999; 1572-915X
Additional Links:
http://link.springer.com/10.1007/s10687-015-0230-4
Appears in Collections:
Articles; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorHuser, Raphaëlen
dc.contributor.authorDavison, Anthony C.en
dc.contributor.authorGenton, Marc G.en
dc.date.accessioned2015-12-16T13:07:23Zen
dc.date.available2015-12-16T13:07:23Zen
dc.date.issued2015-11-17en
dc.identifier.citationLikelihood estimators for multivariate extremes 2015 Extremesen
dc.identifier.issn1386-1999en
dc.identifier.issn1572-915Xen
dc.identifier.doi10.1007/s10687-015-0230-4en
dc.identifier.urihttp://hdl.handle.net/10754/583987en
dc.description.abstractThe main approach to inference for multivariate extremes consists in approximating the joint upper tail of the observations by a parametric family arising in the limit for extreme events. The latter may be expressed in terms of componentwise maxima, high threshold exceedances or point processes, yielding different but related asymptotic characterizations and estimators. The present paper clarifies the connections between the main likelihood estimators, and assesses their practical performance. We investigate their ability to estimate the extremal dependence structure and to predict future extremes, using exact calculations and simulation, in the case of the logistic model.en
dc.language.isoenen
dc.publisherSpringer Science + Business Mediaen
dc.relation.urlhttp://link.springer.com/10.1007/s10687-015-0230-4en
dc.rightsArchived with thanks to Extremes. The final publication is available at Springer via http://dx.doi.org/10.1007/s10687-015-0230-4.en
dc.subjectAsymptotic relative efficiencyen
dc.subjectCensored likelihooden
dc.subjectLogistic modelen
dc.subjectMultivariate extremesen
dc.subjectPairwise likelihooden
dc.subjectPoint process approachen
dc.titleLikelihood estimators for multivariate extremesen
dc.typeArticleen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journalExtremesen
dc.eprint.versionPost-printen
dc.contributor.institutionEPFL, FSB-MATHAA-STAT, Station 8, Bâtiment MA, 1015, Lausanne, Switzerlanden
dc.contributor.affiliationKing Abdullah University of Science and Technology (KAUST)en
kaust.authorHuser, Raphaëlen
kaust.authorGenton, Marc G.en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.