Practical Volatility and Correlation Modeling for Financial Market Risk Management

Torben G. Andersen, Tim Bollerslev, Peter F. Christoffersen and Francis X. Diebold

in The Risks of Financial Institutions

Published by University of Chicago Press

Published in print February 2007 | ISBN: 9780226092850
Published online February 2013 | e-ISBN: 9780226092980 | DOI:
Practical Volatility and Correlation Modeling for Financial Market Risk Management

Show Summary Details


This chapter demonstrates how important it is to recognize time-varying volatility and correlation in value at risk estimation. It also illustrates how new techniques in multivariate time-series estimation could be usefully brought to bear to address some of the problems that pushed banks toward historical simulation and stress testing. Then, it considers various strategies for modeling and forecasting realized covariances, treating them as directly observable vector time series. Standard model-free methods rely on false assumptions of independent returns. Generalized autoregressive conditional heteroskedastic (GARCH) volatility models provide a convenient and parsimonious framework for modeling key dynamic features of returns. Recent advances in multivariate GARCH modeling are likely to be useful for medium-scale models. Volatility measures based on high-frequency return data hold great promise for practical risk management. Risk management requires fully specified conditional density models, not just conditional covariance models.

Keywords: risk estimation; modeling; volatility models; risk management; covariance models; time-varying volatility; multivariate time-series

Chapter.  12963 words.  Illustrated.

Subjects: Financial Markets

Full text: subscription required

How to subscribe Recommend to my Librarian

Users without a subscription are not able to see the full content. Please, subscribe or login to access all content.