Non-Linear DSGE Models, The Central Difference Kalman Filter, and The Mean Shifted Particle Filter
63 Pages Posted: 27 May 2008 Last revised: 17 Jun 2008
Date Written: June 17, 2008
This paper shows how non-linear DSGE models with potential non-normal shocks can be estimated by Quasi-Maximum Likelihood based on the Central Difference Kalman Filter (CDKF). The advantage of this estimator is that evaluating the quasi log-likelihood function only takes a fraction of a second. The second contribution of this paper is to derive a new particle filter which we term the Mean Shifted Particle Filter (MSPF). We show that the MSPF outperforms the standard Particle Filter by delivering more precise state estimates, and in general the MSPF has lower Monte Carlo variation in the reported log-likelihood function.
Keywords: Multivariate Stirling interpolation, Particle Filtering, Non-linear DSGE models, Non-normal shocks, Quasi-Maximum Likelihood
JEL Classification: C13, C15, E10, E32
Suggested Citation: Suggested Citation