Estimating nonlinear DSGE models with moments based methods

This article suggests new approach to approximation of moments of nonlinear DSGE models. These approximations are fast and accurate enough to use them for estimation of parameters of nonlinear DSGE models. A small financial DSGE model is repeatedly estimated by several approaches. Approximations of moments are close to moments calculated for large sample simulations. The quality of estimation with suggested approach is close to the Central Difference Kalman Filter (CDKF) based. At the same time suggested approach is much faster.