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.

Highlights

  • Modelling the short-term dynamics of real gross domestic product (GDP) is paramount to economic policy

  • The third section contains a case study in which we focus on the application of our two models to forecasting the dynamics of Romania’s real GDP

  • We demonstrate the relevance and usefulness of a dynamic factor model approach to forecasting real GDP growth

Read more

Summary

Introduction

Modelling the short-term dynamics of real GDP is paramount to economic policy. Of the many statistical approaches that have been used in this area recently, principal components analysis stands out as a preferred choice because it integrates large sets of variables in frameworks that rely on only a few common factors used to produce nowcasts and forecasts of economic output. As we shall discuss later, the dynamic multifactor model uses spectral density analysis to assess the dependence of GDP on several economic and noneconomic variables and subsequently produces forecasts (or, if needed, nowcasts) of GDP based on the generalized principal components technique. Afterwards, we propose a alternative model building on the work of [4];[5] and based on the mechanics of standard (static) principal components analysis This model is similar in concept to the dynamic multifactor model but, as we shall see later, it has some limitations. We provide it in order to assess empirically whether resorting to complex dynamic data analysis leads to an improvement in performance compared with conceptually simpler models. The fourth section concludes and discusses further action to be taken in order to improve the performance and the accuracy of the models

Literature review
Findings
Conclusions
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call