A multifactor approach to forecasting Romanian gross domestic product (GDP) in the short run
Open Access
- 24 July 2017
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 12 (7) , e0181379
Abstract
The purpose of this paper is to investigate the application of a generalized dynamic factor model (GDFM) based on dynamic principal components analysis to forecasting short-term economic growth in Romania. We have used a generalized principal components approach to estimate a dynamic model based on a dataset comprising 86 economic and non-economic variables that are linked to economic output. The model exploits the dynamic correlations between these variables and uses three common components that account for roughly 72% of the information contained in the original space. We show that it is possible to generate reliable forecasts of quarterly real gross domestic product (GDP) using just the common components while also assessing the contribution of the individual variables to the dynamics of real GDP. In order to assess the relative performance of the GDFM to standard models based on principal components analysis, we have also estimated two Stock-Watson (SW) models that were used to perform the same out-of-sample forecasts as the GDFM. The results indicate significantly better performance of the GDFM compared with the competing SW models, which empirically confirms our expectations that the GDFM produces more accurate forecasts when dealing with large datasets.Keywords
This publication has 34 references indexed in Scilit:
- Determining the Number of Factors from Empirical Distribution of EigenvaluesReview of Economics and Statistics, 2010
- Determining the Number of Primitive Shocks in Factor ModelsJournal of Business & Economic Statistics, 2007
- A Generalised Dynamic Factor Model for the Belgian Economy - Useful Business Cycle Indicators and GDP Growth ForecastsSSRN Electronic Journal, 2006
- The Generalized Dynamic Factor ModelJournal of the American Statistical Association, 2005
- Factor forecasts for the UKJournal of Forecasting, 2005
- Forecasting Using Principal Components From a Large Number of PredictorsJournal of the American Statistical Association, 2002
- Coincident and Leading Indicators for the Euro AreaThe Economic Journal, 2001
- The Generalized Dynamic-Factor Model: Identification and EstimationReview of Economics and Statistics, 2000
- A One-Factor Multivariate Time Series Model of Metropolitan Wage RatesJournal of the American Statistical Association, 1981
- The Scree Test For The Number Of FactorsMultivariate Behavioral Research, 1966