Posterior Inference on Parameters in a Nonlinear DSGE Model via Gaussian-Based Filters
- 27 Downloads
This paper studies Gaussian-based filters within the pseudo-marginal Metropolis Hastings (PM-MH) algorithm for posterior inference on parameters in nonlinear DSGE models. We implement two Gaussian-based filters to evaluate the likelihood of a DSGE model solved to second and third order and embed them into the PM-MH: Central Difference Kalman filter (CDKF) and Gaussian mixture filter (GMF). The GMF is adaptively refined by splitting a mixture component into new mixture components based on Binomial Gaussian mixture. The overall results indicate that the estimation accuracy of the CDKF and the GMF is comparable to that of the particle filter (PF), except that the CDKF generates biased estimates in the extremely nonlinear case. The proposed GMF generates the most accurate estimates among them. We argue that the GMF with PM-MH can converge to the true and invariant distribution when the likelihood constructed by infinite Gaussian mixtures weakly converges to the true likelihood. In addition, we show that the Gaussian-based filters are more efficient than the PF in terms of effective computing time. Finally, we apply the method to real data.
KeywordsNonlinear DSGE Central Difference Kalman filter Gaussian mixture filter Pseudo-marginal MH Pseudo posterior
JEL ClassificationC11 E1
- Achieser, N. I. (2013). Theory of approximation. North Chelmsford: Courier Corporation.Google Scholar
- Ali-Löytty, S. (2008). On the convergence of the Gaussian mixture filter. Tampere: Tampere University of Technology.Google Scholar
- Binning, A. & Maih, J. (2015). Sigma point filters for dynamic nonlinear regime switching models. Working paper, Norges Bank. https://ideas.repec.org/p/bno/worpap/2015_10.html.
- Fernández-Villaverde, J., & Levintal, O. (2016). Solution methods for models with rare disasters. Technical report, National Bureau of Economic Research.Google Scholar
- Hall, P., & Heyde, C. C. (2014). Martingale limit theory and its application. Cambridge: Academic Press.Google Scholar
- Jazwinski, A. H. (1970). Stochastic processes and filtering theory. Cambridge: Academic Press.Google Scholar
- Julier, S. J., & Uhlmann, J. K. (1997). A new extension of the Kalman filter to nonlinear systems. In International symposium of aerospace/defense sensing, simulation and controls (Vol. 3, No. 26, pp. 182–193). https://doi.org/10.1117/12.280797.
- McLachlan, G., & Peel, D. (2004). Finite mixture models. New York: Wiley.Google Scholar
- Meyn, S. P., & Tweedie, R. L. (2012). Markov chains and stochastic stability. Berlin: Springer.Google Scholar
- Rudebusch, G. D., & Swanson, E. T. (2012). The bond premium in a DSGE model with long-run real and nominal. American Economic Journal: Macroeconomics, 4(1), 105–143.Google Scholar
- Sims, E. R. (2011). Permanent and transitory technology shocks and the behavior of hours: A challenge for DSGE models. Working paper, University of Notre Dame.Google Scholar
- Van Der Merwe, R., & Wan, E. A. (2003). Gaussian mixture sigma-point particle filters for sequential probabilistic inference in dynamic state-space models. In 2003 IEEE international conference on acoustics, speech, and signal processing, 2003. Proceedings (ICASSP’03) (Vol. 6, VI–701). https://doi.org/10.1109/ICASSP.2003.1201778.
- Vats, D., Flegal, J. M., & Jones, G. L. (2017). Multivariate output analysis for Markov chain Monte Carlo. Working paper. arXiv:1512.07713.