Investigating Volatility Behaviour: Empirical Evidence From Islamic Stock Indices

The main purpose of this research is to apply five univariate GARCH models to the daily stock returns of four major sharia stock indices. Two symmetric versions of the GARCH model (GARCH and MGARCH) and three asymmetric versions (EGARCH, TGARCH and PGARCH) are employed to estimate and forecast the volatility of four major sharia indices. The results provide strong evidence that all models can depict the volatility behaviours in all four sharia index returns. The two symmetric models indicate that the volatility of a sharia index’s returns depend on its previous own lags, and statistically prove that a rise in volatility (risk) leads to an increase in mean (return), i.e. the risk premium effect. Meanwhile, the three asymmetric models suggest that negative shocks to daily returns tend to have higher impact on the volatility of sharia indices than positive shocks of the same magnitude. Moreover, based on the values of forecasting errors – root mean square errors (RMSE) and mean absolute errors (MAE) – the asymmetric GARCH models outperform the symmetric models in forecasting the volatility of four major sharia indices. However, the very small difference values of RMSE and MAE among the univariate GARCH-type models denote that no single model is superior to the others.