ECONOMIC-DYNAMICS WITH LEARNING - NEW STABILITY RESULTS

Drawing upon recent contributions in the statistical literature, we pr esent new results on the convergence of recursive, stochastic algorith ms which can be applied to economic models with learning and which gen eralize previous results. The formal results provide probability bound s for convergence which can be used to describe the local stability un der learning of rational expectations equilibria in stochastic models. Economic examples include local stability in a multivariate linear mo del with multiple equilibria and global convergence in a model with a unique equilibrium.