EcoSta 2021: Start Registration
View Submission - EcoSta2021
A0748
Title: Disjoint and sliding blocks estimators for heavy tailed time series Authors:  Rafal Kulik - University of Ottawa (Canada) [presenting]
Abstract: Multivariate regularly varying time series with both weak and strong dependence are considered. Using probabilistic tools developed recently, we will study estimators of so-called cluster functionals. These cluster functionals quantify extremal clustering. We will present the asymptotic theory for disjoint blocks and sliding blocks estimators in the peak-over-threshold framework. In particular, we will show that both classes of estimators have the same asymptotic variance. This is in contrast to the situation when the block maxima method is implemented. Some open questions, especially in the context of long memory, will be presented.