Working Paper: CEPR ID: DP9469
Authors: Robert Kollmann
Abstract: This paper develops a novel approach for estimating latent state variables of Dynamic Stochastic General Equilibrium (DSGE) models that are solved using a second-order accurate approximation. I apply the Kalman filter to a state-space representation of the second-order solution based on the ?pruning? scheme of Kim, Kim, Schaumburg and Sims (2008). By contrast to particle filters, no stochastic simulations are needed for the filter here--the present method is thus much faster. In Monte Carlo experiments, the filter here generates more accurate estimates of latent state variables than the standard particle filter. The present filter is also more accurate than a conventional Kalman filter that treats the linearized model as the true data generating process. Due to its high speed, the filter presented here is suited for the estimation of model parameters; a quasi-maximum likelihood procedure can be used for that purpose
Keywords: Estimation of DSGE models; Kalman filter; Latent state filtering; Particle filter; Pruning; Quasi-maximum likelihood; Second-order approximation
JEL Codes: C63; C68; E37
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| Kalman filter method (C53) | accuracy of estimating latent state variables (C51) |
| Kalman filter (C53) | accuracy compared to standard particle filters (C52) |
| Kalman filter (C53) | accuracy compared to conventional Kalman filter (C53) |
| Kalman filter method (C53) | accuracy of parameter estimation (C51) |