SFB 649 -II: Dynamic semi-parametric modeling (TP B 1)

The project area B1 engages in the dynamic semi-parametric modeling of risk factors. In the foreground is the GPLSIM (generalized partially linear model) class for panel-regression and DSFMs (dynamic semi-parametric factor models). The main direction of this research project is the development and implementation of the statistical theory of this model class and its use on the dynamics of the SPD and on panel data. In doing so extreme computationally extensive procedures will be used (theoretically extensively yet unresearched). The empirical calibration comes from the data sources (e. g. high frequency option price time-series, macro time-series), that are generated in connection with the FEDC. The developed procedures will be used by projects B2, B3, B4 and economical modeling of the received VAR time-series together with the projects C1, C2.