Footnote:
Nach Informationen von SSRN wurde die ursprüngliche Fassung des Dokuments April 28, 2017 erstellt
Description:
We evaluated the performance of multivariate models for forecasting Value at Risk (VaR), Expected Shortfall (ES) and Expectile Value at Risk (EVaR). We used Historical Simulation (HS), Dynamic Conditional Correlation-Generalized Autoregressive Conditional Heteroskedastic (DCC-GARCH) and copula methods: Regular copulas, Vine copulas and Nested Archimedean copulas. We assessed the performance of the models using Monte Carlo simulations, considering different scenarios, with regard to the marginal distributions, correlation and number the assets of portfolio. Numerical results evidenced that the accuracy forecasting risk measure is associated with marginal distributions. For a data generating process where the marginal distribution is Gaussian, Regular and Vine copulas demonstrated better performance. For data generated with Student's t distribution, we verified a better performance by Nested Archimedean copulas. In addition, we identified the superiority of copula methods over Historical Simulation and DCC-GARCH, which reduces the model risk