Combining country-specific forecasts when forecasting Euro area macroeconomic aggregates
European Monetary Union member countries’ forecasts are often combined to obtain the forecasts of the Euro area macroeconomic aggregate variables. The aggregation weights which are used to produce the aggregates are often considered as combination weights. This paper investigates whether using different combination weights instead of the usual aggregation weights can help to provide more accurate forecasts. In this context, we examine the performance of equal weights, the least squares estimators of the weights, the combination method recently proposed by Hyndman et al. (Comput Stat Data Anal 55(9):2579–2589, 2011) and the weights suggested by shrinkage methods. We find that some variables like real GDP and the GDP deflator can be forecasted more precisely by using flexible combination weights. Furthermore, combining only forecasts of the three largest European countries helps to improve the forecasting performance. The persistence of the individual series seems to play an important role for the relative performance of the combination.
KeywordsForecast combination Aggregation Macroeconomic forecasting Hierarchical time series Persistence in data
JEL ClassificationC22 C43 C53
I thank the participants of the Doctoral Seminar on Econometrics at the University of Konstanz, the Konstanz–Lancaster Workshop on Finance and Econometrics, the Annual Meeting of the Austrian Economic Association 2015 and the Jahrestagung der Statistischen Woche 2015 for helpful comments and suggestions. Financial support by the Deutsche Forschungsgemeinschaft, Project Number BR 2941/1-2, is gratefully acknowledged.
- Fagan G, Henry J, Mestre R (2001) An area-wide model for the Euro area. In: Working Papers 42, European Central BankGoogle Scholar
- Granger CWJ (1990) Aggregation of time-series variables: a survey. In: Barker T, Pesaran MH (eds) Disaggregation in econometric modelling. Routledge Revivals, London, pp 17–34Google Scholar
- Hendry DF, Clements MP (2004) Pooling of forecasts. Econ J 7(1):1–31Google Scholar
- Hendry DF, Hubrich K (2006) Forecasting economic aggregates by disaggregates. In: Working Papers 589, European Central BankGoogle Scholar
- Hyndman RJ, Lee AJ, Wang E (2014) Fast computation of reconciled forecasts for hierarchhier and grouped time series. In: Working paper 17/14, Department of Econometrics and Business Statistics, Monash UniversityGoogle Scholar
- Lütkepohl H (1984a) Forecasting contemporaneously aggregated vector ARMA processes. J Bus Econ Stat 2(3):201–214Google Scholar
- Lütkepohl H (2010) Forecasting aggregated time series variables: a survey. OECD J J Bus Cycle Meas Anal 2010(2):37–62Google Scholar
- Zellner A (1986) On assessing prior distributions and bayesian regression analysis with g-prior distributions. In: Goel PK, Zellner A (eds) Bayesian inference and decision techniques: essays in honour of Bruno de Finetti. North Holland, AmsterdamGoogle Scholar