Likelihood Evaluation for Dynamic Latent Variables Models
Nov 30 1989
We propose a general Monte Carlo simulation technique for evaluating the likelihood function of dynamic latent variable models, based on artificial factorization of the sequential joint density of the observable and latent variables. The feasibility of the proposed technique is demonstrated by means of a pilot application to a one-parameter disequilibrium model. Extensions to models with weakly exogenous variable and the use of acceleration methods are discussed.