Volatility specifications versus probability distributions in VaR forecasting
-
Laura Garcia-Jorcano [1] ; Alfonso Novales [2]
-
[1] Universidad de Castilla-La Mancha
Universidad de Castilla-La Mancha
Ciudad Real, España
-
[2] Universidad Complutense de Madrid
Universidad Complutense de Madrid
Madrid, España
-
- Localización: Documentos de Trabajo (ICAE), ISSN-e 2341-2356, Nº. 26, 2019, págs. 1-39
- Idioma: inglés
- Enlaces
-
Resumen
We provide evidence suggesting that the assumption on the probability distribution for return innovations is more influential for Value at Risk (VaR) performance than the conditional volatility specification. We also show that some recently proposed asymmetric probability distributions and the APARCH and FGARCH volatility specifications beat more standard alternatives for VaR fore- casting, and they should be preferred when estimating tail risk.
The flexibility of the free power parameter in conditional volatility in the APARCH and FGARCH models explains their better performance. Indeed, our estimates suggest that for a number of financial assets, the dynamics of volatility should be specified in terms of the conditional standarddeviation. Wedrawourresults on VaRforecastingperformance fromi) a variety of back testing approaches, ii) the Model Confidence Set approach, as well as iii) establishing a ranking among alternative VaR models using a precedence criterion that we introduceinthispaper.
