----------------------------------------------------------------------------------------- GIOVEDI 26 LUGLIO DIPARTIMENTO DI STATISTICA PROBABILITA' E STATISTICHE APPLICATE UNIVERSITA' DI ROMA LA SAPENZA PIAZZ.LE ALDO MORO 5 - ROMA SVETLOZAR RACHEV University of California, Santa Barbara and University of Karlsruhe, Germany STABLE MODELING OF MARKET AND CREDIT VALUE AT RISK Abstract The use of stable Paretian distributions in modeling market and credit Value at Risk (VaR) will be examined. The in-sample- and forecast-evaluations show that stable market VaR modeling outperforms the “normal” modeling for high values of the VaR confidence level. The article also develops a new technique for estimating correlation, constructs a new method for simulating portfolio values, and assesses portfolio VaR in various cases of credit instruments’ distributions: independent, symmetric dependent, and skewed dependent. |