|
Activity Number:
|
108
- Multivariate Extremes: Theory and Applications
|
|
Type:
|
Invited
|
|
Date/Time:
|
Monday, July 29, 2019 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Risk Analysis
|
|
Abstract #300290
|
|
|
Title:
|
Semiparametric Estimation for Multivariate Extremes
|
|
Author(s):
|
John P Nolan* and Anne-Laure Fougeres and Cecile Mercadier
|
|
Companies:
|
American University and Univesrity of Lyon and University of Lyon
|
|
Keywords:
|
extreme values;
multivariate;
semi-parametric;
max-projections
|
|
Abstract:
|
Modeling multivariate extremes is an interesting problem because many problems involve multiple observations; it is a challenging problem because the joint distribution involves estimating a measure; an infinite dimensional problem. We present an approach to fitting such models based on two principles. First, classes of semi-parametric models are described that can approximate any extreme value distribution. Second, an estimation method based on max-projections is used to make the estimation problem tractable. An R package mvevd that implements this approach is described.
|
Authors who are presenting talks have a * after their name.
