Backtesting Extreme Value Theory models of expected shortfall

Alfonso Novales ^[1] ; Laura Garcia-Jorcano ^[2]
1. [1] Universidad Complutense de Madrid
  
  Universidad Complutense de Madrid
  
  Madrid, España
2. [2] Universidad de Castilla-La Mancha
  
  Universidad de Castilla-La Mancha
  
  Ciudad Real, España
Localización: Documentos de Trabajo (ICAE), ISSN-e 2341-2356, Nº. 24, 2019, págs. 1-51
Idioma: inglés
Enlaces
- Texto completo (pdf)

Resumen
- We use stock market data to analyze the quality of alternative models and proceduresfor fore- casting expected shortfall (ES) at different significance levels. We compute ES forecasts from conditional models applied to the full distribution of returns as well asfrom modelsthat focus on tail events using extreme value theory (EVT). We also apply the semiparametric filtered historical simulation (FHS) approach to ES forecasting to obtain 10-day ES forecasts. At the 10-day hori- zon we also combine FHS with EVT. The performance of the different models is assessed using six differentES backtests recentlyproposedintheliterature.Ourresultssuggestthatconditional EVT-basedmodelsproducemore accurate 1-day and 10-day ES forecasts than do non-EVT based models. Under either approach, asymmetric probability distributions for return innovations tend to produce better forecasts.
  
  Incorporating EVT in parametric or semiparametric approaches also improves ES forecasting performance. These qualitative results are alsovalidforthe recent crisis period, even though all models then underestimate the level of risk. FHS narrows the range of numerical forecasts obtained from alternative models, thereby reducing model risk. Combining EVT and FHS seemsto be best approach forobtainingaccurateESforecasts.