298.Modelling and Forecasting Fiscal Variables for the Euro Areaby Carlo A. Favero and Massimiliano Marcellino
In this paper we assess the possibility of producing unbiased forecasts for fiscal variables in theeuro area by comparing a set of procedures that rely on different information sets andeconometric techniques. In particular, we consider ARMA models, VARs, small scale semi-structural models at the national and euro area level, institutional forecasts (OECD), andpooling. Our small scale models are characterized by the joint modelling of fiscal and monetarypolicy using simple rules, combined with equations for the evolution of all the relevantfundamentals for the Maastricht Treaty and the Stability and Growth Pact. We rank models onthe basis of their forecasting performance using the mean square and mean absolute errorcriteria at different horizons. Overall, simple time series methods and pooling work well and areable to deliver unbiased forecasts, or slightly upward biased forecast for the debt-GDPdynamics. This result is mostly due to the short sample available, the robustness of simplemethods to structural breaks, and to the difficulty of modelling the joint behaviour of severalvariables in a period of substantial institutional and economic changes. A bootstrap experimenthighlights that, even when the data are generated using the estimated small scale multi country model, simple time series models can produce more accurate forecasts, due totheir parsimonious specification.
JEL Classification: C53, C30, E62
Keywords: Fiscal forecasting, Forecasting comparison, Fiscal rules, Euro area
Download PDF Document
IGIER - Università Bocconi