By studying the ability of the Normal Tempered Stable (NTS) model to fit the statistical
features of intraday data at a 5 min sampling frequency Florian Jacobs extends the research on
high frequency data as well as the appliance of tempered stable models. He examines the DAX30
returns using ARMA-GARCH NTS ARMA-GARCH MNTS (Multivariate Normal Tempered Stable) and
ARMA-FIGARCH (Fractionally Integrated GARCH) NTS. The models will be benchmarked through their
goodness of fit and their VaR and AVaR as well as in an historical Backtesting.
