A regime-switching regression model for hedge funds

  • The modelling of hedge funds poses a difficult problem since the available reported data sets are often small and incomplete. We propose a switching regression model for hedge funds, in which the coefficients are able to switch between different regimes. The coefficients are governed by a Markov chain in discrete time. The different states of the Markov chain represent different states of the economy, which influence the performance of the independent variables. Hedge fund indices are chosen as regressors. The parameter estimation for the switching parameter as well as for the switching error term is done through a filtering technique for hidden Markov models developed by Elliott (1994). Recursive parameter estimates are calculated through a filter-based EM-algorithm, which uses the hidden information of the underlying Markov chain. Our switching regression model is applied on hedge fund series and hedge fund indices from the HFR database.

Export metadata

  • Export Bibtex
  • Export RIS

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Author:Ch. Erlwein, M. Müller
URN (permanent link):urn:nbn:de:hbz:386-kluedo-16801
Serie (Series number):Berichte des Fraunhofer-Instituts für Techno- und Wirtschaftsmathematik (ITWM Report) (199)
Document Type:Report
Language of publication:English
Year of Completion:2010
Year of Publication:2010
Publishing Institute:Fraunhofer-Institut für Techno- und Wirtschaftsmathematik
GND-Keyword:Filtering; Hedge funds ; Optimal parameter estimation ; Switching regression model
Faculties / Organisational entities:Fraunhofer (ITWM)
DDC-Cassification:510 Mathematik

$Rev: 12793 $