Bayesian analysis of moment restriction models using nonparametric priors

Résumé

This paper develops a Bayes procedure for moment restriction models. A nonparametric prior is employed to carry out Bayesian analysis without imposing parametric distributional assumptions. Projection methods are used to deal with problems associated with identifying restrictions. A semiparametric Bernstein-von Mises theorem is proved for the finite dimensional parameters. The procedure is implemented with MCMC algorithms.