Simulation-Based Estimation of Models with Lagged Latent Variables.

We extend here our earlier work (Laroque-Salanie, 1989) and propose a dynamic simulated pseudo-maximum likelihood method to deal with a very general class of dynamic non-linear models, including models with lagged latent variables. We test this method on Monte Carlo-generated data for a canonical disequilibrium model. It appears to provide very satisfactory estimates at little computational cost. However, accurate estimation of the standard errors of the estimates may require some care in non-differentiable models. Copyright 1993 by John Wiley & Sons, Ltd.