BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:A geometric interpretation of multivariate extreme value analysis
DTSTART:20250617T120000Z
DTEND:20250617T130000Z
DTSTAMP:20260610T152500Z
UID:indico-event-14398@indico.math.cnrs.fr
DESCRIPTION:Speakers: Ryan Campbell (Lancaster University)\n\nIn extreme v
 alue analysis\, interest lies in characterising the tail behaviour of rand
 om vectors. This is difficult\, since different combinations of the vector
 's components can exhibit different tail dependence properties. In this ta
 lk\, theory and methodology will be introduced to bypass these difficultie
 s by studying the geometry of random vectors\, with a view to perform infe
 rence on the multivariate tail. Two methods to estimate this geometry give
 n data will be presented. The first relies on parametric assumptions. The 
 second is semi-parametric\, interpolating the domain of the underlying ran
 dom vector in a piecewise-linear manner. This results in a simple construc
 tion that is flexible on data with extremal dependence behaviour that is d
 ifficult to parameterise\, and is more suitable for higher-dimensional app
 lications. The piecewise-linear approach can be useful in defining a radia
 l and an angular model\, allowing for the joint fitting of extremal pseudo
 -polar coordinates\, a key feature of the geometric approach. The new meth
 odology is applied to model high urban air pollution measurements\, a sett
 ing where classical multivariate extremes methods often struggle due to th
 e potential combination of dependence and independence in the joint tails.
 \nJoint work with my PhD supervisor\, Jennifer Wadsworth\, at Lancaster Un
 iversity.\n\nhttps://indico.math.cnrs.fr/event/14398/
URL:https://indico.math.cnrs.fr/event/14398/
END:VEVENT
END:VCALENDAR