Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/319609 
Year of Publication: 
2025
Series/Report no.: 
Bank of Finland Research Discussion Papers No. 6/2025
Publisher: 
Bank of Finland, Helsinki
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.
Subjects: 
Nowcasting
Real-time analysis
Vector autoregressions
Bayesian methods
Mixed frequency
Business cycles
JEL: 
C11
C52
C53
E32
E37
Persistent Identifier of the first edition: 
Document Type: 
Working Paper

Files in This Item:
File
Size





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.