Title: Filter-based discrete-time EM algorithm with diffusion and point process observation
Authors: Camilla Damian - WU Vienna University of Economics and Business (Austria) [presenting]
Zehra Eksi-Altay - WU Wirtschaftsuniversitaet Wien (Austria)
Ruediger Frey - WU Wirtschaftsuniversitaet Wien (Austria)
Abstract: The focus is on statistical inference in a dynamic, reduced-form, partial-information model for Eurozone sovereign credit spreads. The main assumption is that default intensities are driven by an unobservable finite-state Markov chain. Regarding methodology, an extension of the EM algorithm is involved: instead of pure diffusion information, both diffusive and point-process observations are considered. In the financial application, the point process represents default history of a given country. The goal is to estimate the model parameters, in particular the infinitesimal generator of the underlying Markov chain, making use of the robust discretization of continuous-time filters. Both a simulation analysis, which is essential to check performance, accuracy and stability of the algorithm, and an application to real data are presented.