Extreme value theory performance in the event of major financial crises
by Adrian F. Rossignolo; Meryem Duygun Fethi; Mohamed Shaban
International Journal of Banking, Accounting and Finance (IJBAAF), Vol. 4, No. 2, 2012

Abstract: Current directives issued by the Basel Committee have established value-at-risk (VaR) as the standard measure to quantify market risk. In view of the wide range of applications and regulatory requirements, the development of accurate techniques becomes a topic of prime importance. VaR should protect market participants against sudden jerks in financial markets. While most models achieve that purpose for common everyday movements, they fail to account for unexpected crises. Extreme value theory (EVT) provides a method to estimate VaR at high quantiles of the distribution focusing on unusual circumstances. This paper employs EVT to calculate VaR for ten stock market indices belonging to developed and emerging markets in two different ways: unconditional EVT on raw returns and conditional EVT through quasi-maximum likelihood. The performance of EVT representations during the 2008 turmoil reveals that this methodology could have helped institutions to avoid huge losses arising from market disasters. A simple exercise on the constitution of Regulatory Capital illustrates the advantages of EVT.

Online publication date: Sat, 23-Aug-2014

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Banking, Accounting and Finance (IJBAAF):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com