This talk has been automatically captioned. You can remove these by pressing CC on the video toolbar.

Name: Anwar Alabdulathem

Talk Title: Tail Index Regression-Adjusted Functional Covariate

Abstract: In this talk I will propose a statistical model the aims to assess how the extreme values of a random variable can change with a functional covariate. The proposed model can be understood as a regression model for heave-tailed response and where the covariate is a random function. To learn about the proposed method a likelihood-based estimator is defined by solving an approximation to a certain variational calculus problem of integral. Simulation data are used to evaluate the performance of the proposed methods. Applications of the proposed methods are envisioned finance, in order to understand how the risk of an extreme loss in the stock market may change according to a certain functional covariate.

This talk is a contributed talk at EVA 2021.