Value-at-Risk and Extreme Returns in Asian Stock Markets

24 Pages Posted: 1 Oct 2003

See all articles by Andre Carvalhal

Andre Carvalhal

The COPPEAD Graduate School of Business

Beatriz V.M. Mendes

Instituto Nacional de Matemática Pura e Aplicada (IMPA)

Abstract

The purpose of this paper is to use the extreme value theory to analyze ten Asian stock markets, identifying which type of extreme value asymptotic distribution better fits historical extreme market events. Understanding the influence of extreme market events is of great importance for risk managers. Our empirical tests indicate that the return distributions are not characterized by normality and that the minima and the maxima of the return series may be satisfactorily modeled within an extreme value framework. The average waiting time for an index to present a daily return below/above a specific threshold is generally larger for Asian major markets than for Asian emerging markets. We also compute VaR estimates using extreme value theory and compare the results with the empirical and normal VaR estimates. The results suggest that the extreme value method of estimating VaR is a more conservative approach to determining capital requirements than traditional methods.

Keywords: Value-at-risk, Extreme values, Asia

JEL Classification: G15, G18

Suggested Citation

Carvalhal, Andre and Mendes, Beatriz V.M., Value-at-Risk and Extreme Returns in Asian Stock Markets. International Journal of Business, Vol. 8, No. 1, 2003, Available at SSRN: https://ssrn.com/abstract=420266 or http://dx.doi.org/10.2139/ssrn.420266

Andre Carvalhal

The COPPEAD Graduate School of Business ( email )

Rua Pascoal Lemme
355 - Cidade Universitária
Rio de Janeiro, Rio de Janeiro 21941-918
Brazil

Beatriz V.M. Mendes (Contact Author)

Instituto Nacional de Matemática Pura e Aplicada (IMPA) ( email )

Estrada Dona Castorina 110
Rio de Janeiro, 22460
Brazil

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
743
Abstract Views
3,176
Rank
64,855
PlumX Metrics