Effects of Level Outliers on the Identification and Estimation of GARCH Models

In this paper, we study the effects caused by the presence of outliers on the identification and estimation of GARCH models. First, we derive the asymptotic biases of the sample autocorrelations of squared observations and their effects on some popular homoscedasticity tests when uncorrelated GARCH series are contaminated by level outliers. Then, we obtain the asymptotic biases of the OLS estimates of the parameters of ARCH(p) models and analyze their finite sample behavior by means of extensive Monte Carlo experiments. The finite sample results are also extended to ML estimates of ARCH(p) and GARCH(1,1) models. The results are illustrated analyzing real series of financial ret