Estimating Nonlinear DSGE Models by the Simulated Method of Moments

Francisco Ruge-Murcia

No 237, 2011 Meeting Papers from Society for Economic Dynamics

Abstract: This paper studies the application of the simulated method of moments (SMM) for the estimation of nonlinear dynamic stochastic general equilibrium (DSGE) models. Monte Carlo analysis is employed to examine the small-sample properties of SMM in specifications with different curvature. Results show that SMM is computationally efficient and delivers accurate estimates, even when the simulated series are relatively short. However, asymptotic standard errors tend to overstate the actual variability of the estimates and, consequently, statistical inference is conservative. A simple strategy to incorporate priors in a method of moments context is proposed. An empirical application to the macroeconomic effects of rare events indicates that negatively skewed productivity shocks induce agents to accumulate additional capital and can endogenously generate asymmetric business cycles.

Date: 2011
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://red-files-public.s3.amazonaws.com/meetpapers/2011/paper_237.pdf (application/pdf)

Related works:
Working Paper: Estimating Nonlinear DSGE Models by the Simulated Method of Moments (2010)
Working Paper: Estimating Nonlinear DSGE Models by the Simulated Method of Moments (2010)
Working Paper: Estimating Nonlinear DSGE Models by the Simulated Method of Moments (2010)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:red:sed011:237

Access Statistics for this paper

More papers in 2011 Meeting Papers from Society for Economic Dynamics Society for Economic Dynamics Marina Azzimonti Department of Economics Stonybrook University 10 Nicolls Road Stonybrook NY 11790 USA. Contact information at EDIRC.
Bibliographic data for series maintained by Christian Zimmermann ().