Nonparametric models for extreme risks with urn models
 
 
Description:  Extreme risk is often modelled with parametric or semi-parametric models. Here we present nonparametric models for a large setup of risks where the underlying process is not stationary, but is changing with time. The approach is based on the flexible class of urn models. This is made possible for univariate risks as well as multivariate risks. These models can be treated theoretically assuming certain restrictions. If these assumptions are not holding one can always simulate the urn model to get estimates of the extreme risk probabilities.
Date:  2017-03-22
Start Time:   14:30
Speaker:  Juerg Husler (Univ. of Bern, Switzerland)
Institution:  Univ. of Bern, Switzerland
Place:  Sala 5.4
Research Groups: -Probability and Statistics
See more:   <Main>  
 
© Centre for Mathematics, University of Coimbra, funded by
Science and Technology Foundation
Powered by: rdOnWeb v1.4 | technical support