|
CRAMÉR-RAO BOUND FOR STOCHASTIC VOLATILITY MODEL
Miroslav Šimandl and Jakub Královec
Department of Cybernetices and
Center for Research of Cybernetic Systems
University of West Bohemia in Pilsen
Univerzitní 8, 306 14 Pilsen, Czech Republic
phone: +420-19-7491171, fax: +420-19-7429050
e-mail: simandl@kky.zcu.cz, kralove2@kky.zcu.cz
Estimation problem for the stochastic volatility (SV) model, which is significant in financial econometrics, is discussed. Recursive relations for computation of the Cramér-Rao (CR) bound are derived for state and parameter estimation of this model. An attention is paid to regularity conditions for CR bound calculation. As the CR bound represents a lower bound of the mean-square error of an estimate, it can serve as a gauge of quality of nonlinear estimators for the SV model.
Keywords: nonlinear models, Cramér-Rao bound, nonlinear filters, financial systems, stochastic systems
Session slot T-Tu-E07: Modeling and Control of Economic Systems/Area code 5e : Computation in Economic, Financial and Engineering-Economic Systems
 | 