Prediction and Validation for Extremes: Benjamin Bobbia
From Belle Taylor
views
comments
From Belle Taylor
This talk has been automatically captioned. You can remove these by pressing CC on the video toolbar.
Name: Benjamin Bobbia
Talk Title: Estimation of extreme conditional quantiles with coupling method
Abstract: The aim of this work is the estimation of extreme quantile of a real random variable conditionally to a covariate in dimension d. In the framework of proportional tails, inspired of the heteroscedatics extremes, we develop a coupling approach based on Wasserstein distance to provide asymptotic results about quantile and tail estimators. Those coupling arguments rely on the control of the Wasserstein distance between empirical measures and sharp bounds between the law of exceedances and the Pareto distribution. This approach also provide a validation procedure for proportional tails model.
This talk is a contributed talk at EVA 2021.
The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336, VAT Registration Number GB 592 9507 00, and is acknowledged by the UK authorities as a “Recognised body” which has been granted degree awarding powers.
Any views expressed within media held on this service are those of the contributors, should not be taken as approved or endorsed by the University, and do not necessarily reflect the views of the University in respect of any particular issue.
Unless explicitly stated otherwise, all material is copyright © The University of Edinburgh 2021 and may only be used in accordance with the terms of the licence.