Fourier inference for stochastic volatility models with heavy-tailed innovations (Q1785815)

The authors study stochastic volatility models which are driven by a heavy-tailed innovation distribution. They propose an estimator which minimizes a weighted \(L_2\)-type distance between the theoretical characteristic function of the transformed observations and an empirical counterpart. A related goodness-of-fit test is also proposed and Monte Carlo results are presented. The procedures are applied to daily observations of the NASDAQ stock price index.