GDP Solera: The Ideal Vintage Mix

Abstract

We use the information in the successive vintages of GDE and GDI to obtain an improved timely measure of U.S. aggregate output by exploiting cointegration between the different measures taking seriously their monthly release calendar. We also combine all existing overlapping comprehensive revisions to achieve further improvements. We pay particular attention to the Great Recession and the COVID-19 pandemic, which, despite producing dramatic fluctuations, did not generate noticeable revisions in previous growth rates. Our results suggest that revised GDE estimates, unlike GDI ones, are increasingly precise and receive higher weights, but early estimates retain some influence.

KEYWORDS:

• Cointegration
• Comprehensive revisions
• Signal extraction
• U.S. aggregate output
• Vintages

Supplementary Materials

The Supplemental Appendix contains detailed proofs of our identification results, further details on estimation and filtering, several model comparisons and robustness exercises, as well as an analysis of the implications of optimal data releases on our filtering procedure and the nesting of the news and noise model in our framework.

Acknowledgments

We would like to thank Boragan Aruoba, Gabriel Pérez Quirós, António Rua, Dongho Song and audiences at the RCEA Webinar Series, the 3rd Italian Workshop of Econometrics and Empirical Economics (Rimini), Banco de Portugal, the XII Time Series Econometrics Workshop (Zaragoza), Universitat de les Illes Balears, the 2022 North American (Miami) and European (Milan) Summer Meetings of the Econometric Society, American University in Cairo, Bank of Spain, XI Encuentro de la SEU (Montevideo), Universidad de Alicante, the 2023 Climate Finance and the Hydrogen Economy Conference (ICADE) and the 2023 Barcelona Workshop in Financial Econometrics (ESADE) for useful comments and suggestions. We are also thankful to Joël Marbet, Utso Pal Mustafi and Clara Arroyo for excellent research assistance. Three anonymous referees provided very useful feedback. Of course, the usual caveat applies. The views expressed in this article are those of the authors and do not necessarily reflect the position of the Federal Reserve Bank of New York or the Federal Reserve System.

Disclosure Statement

No potential conflict of interest was reported by the author(s).

The second and fourth authors gratefully acknowledge financial support from the Spanish Ministry of Science and Innovation through grant PID2021-128963NB-I00, while the third one is grateful to MIUR through the PRIN project “High-dimensional time series for structural macroeconomic analysis in times of pandemic”.