Abstract.
Potentially increasing volatility and downside risk is essential to financial risk management which is concerned with the tails, or particularly, the lower tail, of the distribution of speculative asset returns. Applying extreme value theory, the present paper outlines a simple model capturing time-varying tail behavior and studies conditional daily return quantiles for the German DAX. Our results indicate an overall increased risk of large one-day holding-period losses related to a structural break given by the 1987 crash, systematic out-of-sample underestimation of the magnitude of extreme quantiles as well as clustering in estimated quantile exceedances which cannot be fully explained by the forecasting model.
Similar content being viewed by others
Author information
Authors and Affiliations
Additional information
RID="*"
ID="*" Part of the paper was written while the author was visiting the Center for Mathematical Sciences at Munich University of Technology. He is grateful for the members' hospitality and thanks Claudia Klüppelberg for helpful discussions as well as two anonymous referees for comments improving the paper.
Rights and permissions
About this article
Cite this article
Wagner, N. Estimating financial risk under time-varying extremal return behavior. OR Spectrum 25, 317–328 (2003). https://doi.org/10.1007/s00291-003-0126-6
Issue Date:
DOI: https://doi.org/10.1007/s00291-003-0126-6