[MaPhySto logo] [MPS NEWS]
Vol.2., Issue No. 1. September 2003

Funded by The Danish National Research Foundation

Concentrated Advanced Course on Statistical Methods for Financial Risk Management, Copenhagen, May 26-30, 2003

participant at a coffee break
All participant at a coffee break

This CAC was the first one in the new period of MaPhySto. It was organized by Søren Asmussen (Aarhus), Jeffrey Collamore, Martin Jacobsen, Thomas Mikosch and Michael Sørensen (all Copenhagen) at the H.C. Ørsted Institute of Copenhagen University. The CAC was supported by DYNSTOCH, an EU Research Training Network, and by Adept Scientific, a company which, among other things, distributes the software package Splus in Denmark.

Quantitative methodology is an increasingly important component of risk management in financial institutions. Financial risk management presents an extremely interesting area of application for statistics with many new challenges. Whereas much of traditional statistics concerns the average, the normal and the expected, risk management has more to do with the extreme, the abnormal and the unexpected. Central technical issues are modeling the volatility of financial return time series, modeling extreme values and dependent risks. Those include methods relevant for market and credit risk management. Therefore the CAC offered the unique opportunity to learn from specialists about models for modern risk management and the corresponding statistical problems.

From left to the right: Murad Taqqu, Catalin Starica, Thomas Mikosch and a Superman participant at Amalienborg Castle.

The Main Lecturer of this CAC was Alexander McNeil from ETH Zürich and RiskLab Zürich who has many years of practical experience with the statistics of risk management. Over the last years he has given numerous courses and lectures about the statistics of risks and extremes for representatives of the financial and insurance industries. In his lectures he gave an overview of relevant modern statistical techniques for risk management which he convincingly illustrated by using real-life and simulated data sets, supported by the statistical programming package S+FinMetrics. Because of its practical orientation, the course attracted 75 participants, among them 25 practitioners from banks, insurance companies and regulatory institutions and more than 30 graduate students of statistics, mathematics or economics.

The program of the course was supplemented by key note lectures on different issues of risk management. Henrik Hult (KTH Stockholm) gave a lecture on multivariate regular variation, Thomas Mikosch (Copenhagen University) on multivariate extremes and GARCH processes, Catalin Starica (Chalmers University Gothenburg) on risk-return dynamics in stock indices and on multivariate dynamics of stock returns, Murad Taqqu (Boston University) on stable processes and on local contagion in financial markets.

This CAC aimed at the popularization of statistical techniques for risk management to a wide audience, including the researcher, the graduate student and the practitioner in financial and insurance. It also aimed at bridging the gap between theory and practice in risk management. There was plenty of opportunity during the course to discuss practical problems which the participants had experienced in their own work and for which the material of the course offered some solution.

Alexander McNeil
The exhausted Alexander McNeil after five days of teaching.
Report by Thomas Mikosch