CMStatistics 2018: Start Registration
View Submission - CMStatistics
B1021
Title: Generalized Pareto copulas: A key to multivariate extremes Authors:  Simone Padoan - Bocconi University (Italy) [presenting]
Michael Falk - University of Wuerzburg (Germany)
Abstract: In recent years many efforts have been made by different authors to characterize what a multivariate generalized Pareto distribution is. Generalized Pareto copulas (GPC) are presented. Any GPC can be represented in a simple, analytical way using a particular type of norm on $\mathbb{R}^d$, called D-norm. The characteristic property of a GPC is its {\it exceedance stability}. The GPC turns out to be a key to multivariate extreme value theory. We discuss the inferential aspects related to GPC and we show its utility analyzying a real dataset.