Table 1
GARCH models modification and their applications to oil market volatility.
| Model | Feature | Model | Feature |
|---|---|---|---|
| IGARCH | Is better equipped to account for this long memory in the volatility due to the integration, of the variance equation coefficients of standard GARCH, over lag variables. | GARCH_M | Allows for the mean of the returns to be a function of the conditional volatility. |
| GARCH (FIGARCH) | It captures long memory shocks effectively and provides a slow decay of shocks over time. | Multivariate GARCH | These models are useful when simultaneously computing the volatility of multiple assets. |
| TGARCH & GJR | Adds another residual term to the standard GARCH to account for asymmetrical behavior in volatility. | CGARCH | It improves the modeling of long-term effects by decomposing the model into long-run and short-run components. |
| EGARCH | Unlike the standard GARCH models often restrict coefficients to be positive, this model removes this restriction. | NN-GARCH | A hybrid model that incorporates neural networks with GARCH estimates the extreme values of volatility more effectively than GARCH models alone. |
| HYGARCH | Is a mixture of standard GARCH, IGARCH and FIGARCH models. |
Source: Matar et al. (2013), pp. 255.