香蕉视频

A latent-vine factor-copula time series model for extreme flood insurance losses

听

Abstract:

Vines and factor copula models are handy tools for statistical inference in high dimension. However, their use for assessing and predicting the co-occurrence of rare events is subject to caution when multivariate extreme data are sparse. Motivated by the need to assess the risk of concurrent large insurance claims in the American National Flood Insurance Program (NFIP), I will describe a novel class of copula models that can account for spatio-temporal dependence within clustered sets of time series. This new class, which combines the advantages of vines and factor copula models, provides great flexibility in capturing tail dependence while maintaining interpretability through a parsimonious latent structure. Using NFIP data, I will show the value of this approach in evaluating the risks associated with extreme weather events.

Speaker

Christian听Genest听is听Professor and Canada Research Chair in Stochastic Dependence Modeling at 香蕉视频. His research interests include multivariate analysis, nonparametric statistics, and extreme-value theory.

听

Meeting ID: 891 2156 7327

Passcode: None