Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/61727 
Year of Publication: 
1999
Series/Report no.: 
SFB 373 Discussion Paper No. 1999,105
Publisher: 
Humboldt University of Berlin, Interdisciplinary Research Project 373: Quantification and Simulation of Economic Processes, Berlin
Abstract: 
VaR models are related to statistical forecast systems. Within that framework different forecast tasks including Value-at-Risk and shortfall are discussed and motivated. A backtesting method based on the shortfall is developed and applied to VaR forecasts of areal portfolio. The analysis shows that backtesting based on shortfall is very sensitive with respect to the underlying assumptions.
Persistent Identifier of the first edition: 
Document Type: 
Working Paper

Files in This Item:
File
Size
243.66 kB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.