Tail-Related Risk Measurement and Forecasting in Equity Markets

摘要: Parametric, simulation-based and hybrid methods are utilized to estimate various risk measures such as Value-at-Risk (VaR), Conditional VaR coherent Expected Shortfall. An exhaustive backtesting analysis is performed for London’s FTSE 100 index a comparative evaluation of the predictability investigated models with use statistical tests. We show that optimal tail forecasting necessitates many factors be considered asset structure capitalization specific market conditions i.e., normal or crisis periods. Specifically, large stocks long investment horizons parametric modeling accounted relatively better estimation in quantiles, whilst short-term trading strategies, non-parametric more suitable measuring extreme small-cap stocks.