Economics at your fingertips  

A multifactor approach to forecasting Romanian gross domestic product (GDP) in the short run

Daniel Armeanu, Jean Vasile Andrei, Leonard Lache and Mirela Panait ()

PLOS ONE, 2017, vol. 12, issue 7, 1-23

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.

Date: 2017
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (4) Track citations by RSS feed

Downloads: (external link) (text/html) ... 81379&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link:

DOI: 10.1371/journal.pone.0181379

Access Statistics for this article

More articles in PLOS ONE from Public Library of Science
Bibliographic data for series maintained by plosone ().

Page updated 2023-03-08
Handle: RePEc:plo:pone00:0181379