Multivariate Models to Forecast Portfolio Value at Risk: from the Dot- Com crisis to the global financial crisis
PDF (Português (Brasil))


Stock markets. Value at Risk. Multivariate GARCH models. Extreme value theory. Backtesting.

How to Cite

Gabriel, V. M. de S. (2014). Multivariate Models to Forecast Portfolio Value at Risk: from the Dot- Com crisis to the global financial crisis. Review of Business Management, 16(51), 299–318.


This study analyzed market risk of an international
investment portfolio by means of a new
methodological proposal based on Value-at-
Risk, using the covariance matrix of multivariate
GARCH-type models and the extreme value
theory to realize if an international diversification
strategy minimizes market risk, and to determine
if the VaR methodology adequately captures
market risk, by applying Backtesting tests. To
this end, we considered twelve international
stock indexes, accounting for about 62% of the
world stock market capitalization, and chose the
period from the Dot-Com crisis to the current
global financial crisis. Results show that the
proposed methodology is a good alternative to
accommodate the high market turbulence and
can be considered as an adequate portfolio risk
management instrument.
PDF (Português (Brasil))

If a paper is approved for publication, its copyright has to be transferred by the author(s) to the Review of Business Management – RBGN.

Accordingly, authors are REQUIRED to send RBGN a duly completed and signed Copyright Transfer Form. Please refer to the following template: [Copyright Transfer]

The conditions set out by the Copyright Transfer Form state that the Review of Business Management – RBGN owns, free of charge and permanently, the copyright of the papers it publishes. Although the authors are required to sign the Copyright Transfer Form, RBGN allows authors to hold and use their own copyright without restrictions.

The texts published by RBGN are the sole responsibility of their authors.

The review has adopted the CC-BY Creative Commons Attribution 4.0 allowing redistribution and reuse of papers on condition that the authorship is properly credited.