Bitte verwenden Sie diesen Link, um diese Publikation zu zitieren, oder auf sie als Internetquelle zu verweisen: https://hdl.handle.net/10419/266073 
Erscheinungsjahr: 
2022
Schriftenreihe/Nr.: 
Bank of Canada Staff Discussion Paper No. 2022-12
Verlag: 
Bank of Canada, Ottawa
Zusammenfassung: 
Assessing the state of the economy in real time is critical for policy-making, and understanding the risks to those assessments is equally important. Policy-makers are typically provided with point forecasts that contain insufficient information about risks. In contrast, predictive densities estimate the entire range of possible outcomes. This provides a method for quantifying not only the current state of the economy but also the degree of uncertainty, the tail risks and the overall balance of risks around that state. Accordingly, this paper extends the framework of Chernis and Sekkel (2018) to produce density nowcasts for Canadian real GDP growth. We compare several methods of combining predictive densities from 98 models representing four popular classes of nowcasting models. The performance of these combinations is then assessed in both real-time and pseudo-real-time out-of-sample exercises, with the limited sample real-time simulations reinforcing the importance of data revisions for nowcasting. We demonstrate that the combined densities are reliable and accurate tools for assessing the state of the economy and risks to the outlook. We highlight in particular risks at the start of the COVID-19 pandemic.
Schlagwörter: 
Econometric and statistical methods
JEL: 
C
C5
C52
C53
E
E3
E7
Persistent Identifier der Erstveröffentlichung: 
Dokumentart: 
Working Paper
Erscheint in der Sammlung:

Datei(en):
Datei
Größe
5.62 MB





Publikationen in EconStor sind urheberrechtlich geschützt.