INFLATION FORECASTING FOR AGGREGATES OF THE EU-7 AND EU-14 WITH BAYESIAN VAR MODELS

This article applies the Bayesian Vector Auto-Regressive (BVAR) model to key economic aggregates of the EU-7, consisting of the former narro w-band ERM members plus Austria, and the EU-14. This model appears to be useful as an additional forecasting tool besides structural macroec onomic models, as is shown both by absolute forecasting performance an d by a comparison of ex-post BVAR forecasts with forecasts by the OECD . A comparison of the aggregate models to single-country models reveal s that pooling has a strong impact on forecast errors. If forecast err ors are interpreted as shocks, shocks appear to be-at least in part-as ymmetric, or countries react differently to shocks. (C) 1998 John Wile y & Sons, Ltd.