This talk has been automatically captioned. You can remove these by pressing CC on the video toolbar.
Name: Olivier Wintenberger
Talk Title: Threshold selection for cluster inference based on large deviation principles.
Abstract: In the setting of regularly varying time series, a cluster of exceedances is a short period for which the supremum norm exceeds a high threshold. We propose to study a generalization of this notion considering short periods, or blocks, with norm \ell^p(\R^d) above a large threshold. We derive large deviation principles of blocks and apply these results to improve cluster inference. We focus on block estimators and show they are consistent when we use large quantiles from the sample of \ell^{p}-norm over blocks as threshold levels. Our results lead to a threshold selection method for cluster inference.
This talk is an invited talk at EVA 2021