Authors:
ShinIchi Aihara
1
;
Arunabha Bagchi
2
and
Saikat Saha
3
Affiliations:
1
Tokyo University of Science Suwa, Japan
;
2
Twente University, Netherlands
;
3
Likoping University, Sweden
Keyword(s):
Particle Filter, Stochastic Volatility, Parameter Identification, Adaptive Filter.
Related
Ontology
Subjects/Areas/Topics:
Adaptive Signal Processing and Control
;
Informatics in Control, Automation and Robotics
;
Nonlinear Signals and Systems
;
Optimization Problems in Signal Processing
;
Signal Processing, Sensors, Systems Modeling and Control
;
System Identification
;
System Modeling
Abstract:
We study the sequential identification problem for Bates stochastic volatility model, which is widely used as the model of a stock in finance. By using the exact simulation method, a particle filter for estimating stochastic volatility is constructed. The systems parameters are sequentially estimated with the aid of parallel filtering algorithm. To improve the estimation performance for unknown parameters, the new resampling procedure is proposed. Simulation studies for checking the feasibility of the developed scheme are demonstrated.