Abstract
Particle filters have been widely used for online filtering problems in state–space models (SSMs). The current available proposal distributions depend either only on the state dynamics, or only on the observation, or on both sources of information but are not available for general SSMs. In this article, we develop a new particle filtering algorithm, called the augmented particle filter (APF), for online filtering problems in SSMs. The APF combines two sets of particles from the observation equation and the state equation, and the state space is augmented to facilitate the weight computation. Theoretical justification of the APF is provided, and the connection between the APF and the optimal particle filter (OPF) in some special SSMs is investigated. The APF shares similar properties as the OPF, but the APF can be applied to a much wider range of models than the OPF. Simulation studies show that the APF performs similarly to or better than the OPF when the OPF is available, and the APF can perform better than other filtering algorithms in the literature when the OPF is not available.
Original language | English (US) |
---|---|
Pages (from-to) | 300-313 |
Number of pages | 14 |
Journal | Journal of the American Statistical Association |
Volume | 112 |
Issue number | 517 |
DOIs | |
State | Published - Jan 2 2017 |
Keywords
- Nonlinear filtering
- Particle filter
- Sequential Monte Carlo
- State–space model
ASJC Scopus subject areas
- Statistics and Probability
- Statistics, Probability and Uncertainty