000227007 001__ 227007
000227007 005__ 20180913064244.0
000227007 0247_ $$2doi$$a10.1111/rssb.12157
000227007 022__ $$a1369-7412
000227007 02470 $$2ISI$$a000392486000008
000227007 037__ $$aARTICLE
000227007 245__ $$aModelling across extremal dependence classes
000227007 260__ $$aHoboken$$bWiley-Blackwell$$c2017
000227007 269__ $$a2017
000227007 300__ $$a27
000227007 336__ $$aJournal Articles
000227007 520__ $$aDifferent 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 subdomains 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.
000227007 6531_ $$aAsymptotic independence
000227007 6531_ $$aCensored likelihood
000227007 6531_ $$aConditional extremes
000227007 6531_ $$aDependence modelling
000227007 6531_ $$aExtreme value theory
000227007 6531_ $$aMultivariate regular variation
000227007 700__ $$0246539$$aWadsworth, J. L.$$g226781$$uUniv Lancaster, Lancaster, England
000227007 700__ $$aTawn, J. A.$$uUniv Lancaster, Lancaster, England
000227007 700__ $$0240476$$aDavison, A. C.$$g111184
000227007 700__ $$aElton, D. M.$$uUniv Lancaster, Lancaster, England
000227007 773__ $$j79$$k1$$q149-175$$tJournal Of The Royal Statistical Society Series B-Statistical Methodology
000227007 909C0 $$0252136$$pSTAT$$xU10124
000227007 909CO $$ooai:infoscience.tind.io:227007$$pSB$$particle
000227007 917Z8 $$x111184
000227007 937__ $$aEPFL-ARTICLE-227007
000227007 973__ $$aEPFL$$rREVIEWED$$sPUBLISHED
000227007 980__ $$aARTICLE