High-Dimensional Dynamic Panel with Correlated Random Effects: A Semiparametric Hierarchical Empirical Bayes Approach

A novel multivariate dynamic panel data analysis with correlated random effects is proposed for estimating high-dimensional parameter spaces. A semiparametric hierarchical Bayesian strategy is used to jointly address incidental parameters, endogeneity issues, and model mis-specification problems. The underlying methodology involves an ad-hoc model selection based on conjugate informative proper mixture priors to select promising subsets of predictors affecting outcomes. Monte Carlo algorithms are then conducted on the resulting submodels to construct empirical Bayes estimators and investigate ratio-optimality and posterior consistency for forecasting purposes and policy issues. An empirical approach is applied to a large panel of economies, describing the functioning of the model. Simulations based on Monte Carlo designs are also performed to account for relative regrets dealing with cross-sectional heterogeneity.