Nowcasting in real time: Large Bayesian vector autoregression in a test

Petteri Juvonen and Annika Lindblad

No 6/2025, Bank of Finland Research Discussion Papers from Bank of Finland

Abstract: We analyse the accuracy of an econometric model for nowcasting GDP growth in a true real-time setting. The analysis is based on a unique sample of nowcasts that were produced in real time and stored. Our results support the use of econometric models for nowcasting because the accuracy of these real-time nowcasts is found to be comparable to the first GDP estimates of the statistical authority. The nowcasts are produced by a large Bayesian vector autoregressive model. We find the model fares well against other statistical models, and the results suggest that its performance has been more robust to COVID-19 fluctuations than that of a dynamic factor model. We also analyse comments on the nowcast tweets published on Twitter in real time.

Keywords: Nowcasting; Real-time analysis; Vector autoregressions; Bayesian methods; Mixed frequency; Business cycles (search for similar items in EconPapers)
JEL-codes: C11 C52 C53 E32 E37 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.econstor.eu/bitstream/10419/319609/1/1927850754.pdf (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: https://EconPapers.repec.org/RePEc:zbw:bofrdp:319609

Access Statistics for this paper

More papers in Bank of Finland Research Discussion Papers from Bank of Finland Contact information at EDIRC.
Bibliographic data for series maintained by ZBW - Leibniz Information Centre for Economics ().