Hierarchical analysis of SUR models with extensions to correlated serial errors and time-varying parameter models

We consider the use of Markov chain Monte Carlo methods to analyze hierarchical versions of Zellnerʹs SUR model. In this context, the questions of Bayes estimation and model adequacy checking are considered. The approach is extended to SUR model with vector autoregressive and vector moving average errors of the first order. Finally, an efficient algorithm is developed to estimate a Markov time-varying parameter SUR model. The ideas are applied to both simulated and real data.