Nowcasting GDP and its Components in a Data-Rich Environment: The Merits of the Indirect Approach
116 Pages Posted: 4 Jun 2020 Last revised: 7 Aug 2020
Date Written: May 29, 2020
The national accounts provide a coherent and exaustive description of the current state of the economy, but are available at the quarterly frequency and are released with a nonignorable publication lag. The paper proposes and illustrates a method for nowcasting and forecasting the sixteen main components of Gross Domestic Product (GDP) by output and expenditure type at the monthly frequency, using a high-dimensional set of monthly economic indicators spanning the space of the common macroeconomic and financial factors. The projection on the common space is carried out by combining the individual nowcasts and forecasts arising from all possible bivariate models of the unobserved monthly GDP component and the observed monthly indicator. We discuss several pooling strategies and we select the one showing the best predictive performance according to a pseudo real time forecasting experiment. Monthly GDP can be indirectly estimated by the contemporaneous aggregation of the value added of the different industries and of the expenditure components. This enables the comparative assessment of the indirect nowcasts and forecasts vis-à-vis the direct approach and a growth accounting exercise. Our approach meets the challenges posed by the dimensionality, since it can handle a large number of time series with a complexity that increases linearly with the cross-sectional dimension, while retaining the essential heterogeneity of the information about the macroeconomy. The application to the Italian case leads to several interesting discoveries concerning the time-varying predictive content of the information carried by the monthly indicators.
Keywords: Mixed-Frequency Data, Dynamic Factor Models, Growth Accounting, Model Averaging, Ledoit-Wolf Shrinkage.
JEL Classification: C32, C52, C53, E37
Suggested Citation: Suggested Citation