Alternative methods for forecasting GDP

Dominique Guegan (1, 2) , Patrick Rakotomarolahy (1)

1 CES - Centre d'économie de la Sorbonne
2 PSE - Paris School of Economics

An empirical forecast accuracy comparison of the non-parametric method, known as multivariate Nearest Neighbor method, with parametric VAR modelling is conducted on the euro area GDP. Using both methods for nowcasting and forecasting the GDP, through the estimation of economic indicators plugged in the bridge equations, we get more accurate forecasts when using nearest neighbor method. We prove also the asymptotic normality of the multivariate k-nearest neighbor regression estimator for dependent time series, providing confidence intervals for point forecast in time series.

Mots clés: Forecast; Economic indicators; GDP; Euro area; VAR; Multivariate k nearest neighbor regression; Asymptotic normality

Domaines: Economies et finances; Probabilités [math.PR]; Statistiques [math.ST]; Théorie [stat.TH]

Dominique Guegan, Patrick Rakotomarolahy. Alternative methods for forecasting GDP. R. Barnett, F. Jawady. Nonlinear Modeling of Economic and Financial Time-Series, Emerald Publishers, Chapiter 5 (29 p.), 2010, Series International Symposia in Economic Theory and Econometrics - n°21. ⟨halshs-00511979⟩