Data cloning: Maximum likelihood estimation of DSGE models

Abstract

We present evidence supporting the use of the data cloning method for maximum likelihood estimation of Dynamic Stochastic General Equilibrium models. In the data cloning method, maximum likelihood estimators are obtained as the limit of Bayesian estimators, enjoying the computational advantages of MCMC methods. We present evidences that this method is more robust to initial values than the traditional likelihood estimators in this problem.

Keywords

• Likelihood estimation
• Dynamic Stochastic General Equilibrium
• Bayesian asymptotics