Bayesian Analysis of Dynamic Disequilibrium Models : An Application to the Polish Credit Market

We show how to perform Bayesian inference in dynamic disequilibrium models by data augmentation. Bayesian inference is much simpler than maximum likelihood estimation since multiple integrals that appear in the likelihood function are avoided by working in the spaces of latent and observed variables. This allows to devise a Gibbs sampler which iterates between the latent variables and the parameters. Identification is discussed. An application to credit rationing is provided involving Polish data