RCA model with quadratic GARCH innovation distribution

Rapid development of time series models addressing volatility has recently been reported in the financial literature. Often the standardized residuals from an RCA (Random coefficient autoregressive) model still has fat tails, thus suggesting using a fat-tailed error distribution instead. Kurtosis of GARCH model plays an important role in option pricing applications with real data. This paper considers some volatility models with quadratic GARCH innovations and derive the kurtosis of the process.