Large Deviations of Factor Models with Regularly-Varying Tails: Asymptotics and Efficient Estimation

24 Pages Posted: 14 Mar 2017 Last revised: 20 May 2017

Farzad Pourbabaee

University of California, Berkeley - Department of Economics

Date Written: March 1, 2017

Abstract

I analyze the large deviation probability of factor models generated from components with regularly-varying tails, a large subclass of heavy tailed distributions. An efficient sampling method for tail probability estimation of this class is introduced and shown to exponentially outperform the classical Monte-Carlo estimator, in terms of the coverage probability and/or the confidence interval’s length. The obtained theoretical results are applied to financial portfolios, verifying that deviation probability of the return to portfolios of many securities is asymptotically robust against the distributions of asset specific idiosyncratic risks.

Keywords: Monte-Carlo Method, Tail Estimation, Pareto Distribution

JEL Classification: C13, C15, C38, C58

Suggested Citation

Pourbabaee, Farzad, Large Deviations of Factor Models with Regularly-Varying Tails: Asymptotics and Efficient Estimation (March 1, 2017). Available at SSRN: https://ssrn.com/abstract=2931587

Farzad Pourbabaee (Contact Author)

University of California, Berkeley - Department of Economics ( email )

579 Evans Hall
Berkeley, CA 94709
United States

Paper statistics

Downloads
79
Rank
257,663
Abstract Views
296