Kolokvij će se održati u dvorani A001.
Abstract: Understanding and modelling extremes is a very important issue in various applied fields. Moreover, in data we often observe
(i) really large extremes, and
(ii) extremes occuring in consecutive time units; think of e.g. financial returns or daily rainfall measurements.
This motivates the study of time series models which are both heavy-tailed and time-dependent. In this talk, we will present a general framework for describing the asymptotic distributional behavior of extremes in a large class of such models (so-called regularly varying time series), and illustrate these general results with some simple examples. If time permits, we will comment on how this framework can be extended to deal with extremes of random fields and extremes related to models in stochastic geometry.
