A New Approach to Comparing VaR Estimation Methods

Posted: 20 Apr 2007 Last revised: 21 May 2019

See all articles by Christophe Pérignon

Christophe Pérignon

HEC Paris - Finance Department

Daniel R. Smith

Queensland University of Technology - School of Economics and Finance; Simon Fraser University; Financial Research Network (FIRN)

Date Written: November 1, 2008

Abstract

We develop a novel backtesting framework based on multidimensional Value-at-Risk (VaR) that focuses on the left tail of the distribution of the bank trading revenues. Our coverage test is a multivariate generalization of the unconditional test of Kupiec (Journal of Derivatives, 1995). Applying our method to actual daily bank trading revenues, we find that non-parametric VaR methods, such as GARCH-based methods or filtered Historical Simulation, work best for bank trading revenues.

Keywords: Value-at-Risk, Bank Trading Revenue, Backtesting, Coverage Test

JEL Classification: G21, G28, G32

Suggested Citation

Pérignon, Christophe and Smith, Daniel Robert, A New Approach to Comparing VaR Estimation Methods (November 1, 2008). https://doi.org/10.3905/JOD.2008.16.2.054, Available at SSRN: https://ssrn.com/abstract=981207 or http://dx.doi.org/10.2139/ssrn.981207

Christophe Pérignon

HEC Paris - Finance Department ( email )

1 rue de la Liberation
Jouy-en-Josas Cedex, 78351
France

Daniel Robert Smith (Contact Author)

Queensland University of Technology - School of Economics and Finance ( email )

GPO Box 2434
2 George Street
Brisbane, Queensland 4001
Australia
+61 7 3138 2947 (Phone)
+61 7 3138 2947 (Fax)

Simon Fraser University ( email )

8888 University Drive
Burnaby, British Colombia V5A 1S6
Canada
778-782-4675 (Phone)
778-782-4920 (Fax)

HOME PAGE: http://www.sfu.ca/~drsmith

Financial Research Network (FIRN)

C/- University of Queensland Business School
St Lucia, 4071 Brisbane
Queensland
Australia

HOME PAGE: http://www.firn.org.au

Do you have negative results from your research you’d like to share?

Paper statistics

Abstract Views
7,877
PlumX Metrics