Using a Bayesian framework this paper provides a multivariate combination approach to prediction based on a distributional state space representation of predictive densities from alternative models. In the proposed approach the model set can be incomplete. Several multivariate time-varying...

The literature on agent-based models has been highly successful in replicating many stylized facts of financial and macroeconomic time series. Over the past decade, however, also advances in the estimation of such models have been made. Due to the inherent heterogeneity of agents and...