GARCH volatilities depend on the unconditional variance, which is a non-linear function of the parameters. Consequently, they can have larger biases than estimated parameters. Using robust methods to estimate both parameters and volatilities is shown to outperform Maximum Likelihood procedures.

The main goal when fitting GARCH models to conditionally heteroscedastic time series is to estimate the underlying volatilities. It is well known that outliers affect the estimation of the GARCH parameters. However, little is known about their effects when estimating volatilities. In this paper,...

This paper analyzes the effects caused by outliers on the identification and estimation of GARCH models. We show that outliers can lead to detect spurious conditional heteroscedasticity and can also hide genuine ARCH effects. First, we derive the asymptotic biases caused by outliers on the...

Although the main interest in the modelling of electricity prices is often on volatility aspects, we argue that stochastic heteroskedastic behaviour in prices can only be modelled correctly when the conditional mean of the time series is properly modelled. In this paper we consider different...

The identification of asymmetric conditional heteroscedasticity is often based on sample cross-correlations between past and squared observations. In this paper we analyse the effects of outliers on these cross-correlations and, consequently, on the identification of asymmetric volatilities.We...