Macroeconomic forecasting in the euro area using predictive combinations of DSGE models

We provide a comprehensive assessment of the predictive ability of combinations of Dynamic Stochastic General Equilibrium (DSGE) models for GDP growth, inflation and the interest rate in the euro area. We employ a battery of static and dynamic pooling weights based on Bayesian model averaging principles, prediction pools and dynamic factor representations, and entertain eight different DSGE specifications and four prediction weighting schemes. Our results indicate that exploiting mixtures of DSGE models tends to achieve superior forecasting performance over individual specifications for both point and density forecasts. The largest improvements in the accuracy of GDP growth forecasts are achieved by the prediction pooling technique, while the results for the weighting method based on dynamic factors partly leads to improvements in the quality of inflation and interest rate predictions.