MODELING AND FORECASTING RISK IN ISLAMIC STOCK MARKETS: A COMPREHENSIVE ANALYSIS OF ONE-DAY-AHEAD VaR AND ES USING GARCH MODELS
This paper evaluates the one-day-ahead Value at Risk (VaR) and Expected Shortfall (ES) of two Islamic stock indexes, namely Dow Jones and FTSE. The analysis takes into consideration the presence of volatility clustering, volatility asymmetry, and volatility persistence in the data. Four GARCH-type models, including two fractionally integrated models, were assessed, assuming three alternative distributions (normal, Student-t, and skewed Student-t distributions). The paper considered four GARCH-type models, and the AR (1) - FIEGARCH model under a skewed Student-t distribution was found to perform the best among them. We have computed one-day ahead VaR and (ES) for both short and long trading positions. Back testing results show very clearly that the skewed Student-t FIEGARCH model provides the best results for both short and long VaR estimations.
Long-Range Memory; Value at Risk; Asymmetry; Fat Tail.