In financial time series, the conventional fitting procedure (QMLE) suffers from the outlier problem. Estimation of the parameters in GARCH model, can be adversely affected by a single outlier.
simulation studies will not only demonstrate the robustness of this estimate, but will provide evidence as to the utility, efficiency, and validity of this estimate as a robust procedures.
A large Monte Carlo study over error distributions ranging from heavy-tailed to light-tailed distributions and from symmetric distributions to skewed distributions is conducted to evaluate the robustness of heavy tailed distributions in the presence of additive or innovative outliers which revealed the need of robust estimator other than QMLE in estimating GARCH coefficients in the presence of those outliers.