Efficient Filtering in State-Space Representations
30 Pages Posted: 4 Feb 2009
Date Written: November 30, 2008
We develop a numerical procedure that facilitates efficient filtering in applications involving non-linear and non-Gaussian state-space models. The procedure approximates necessary integrals using continuous approximations of target densities. Construction is achieved via efficient importance sampling, and approximating densities are adapted to fully incorporate current information. We illustrate our procedure for the bearings-only tracking problem.
Keywords: particle filter, adaption, efficient importance sampling, kernel density approximation
JEL Classification: C15, C22
Suggested Citation: Suggested Citation