2017
DOI: 10.1007/s00181-017-1228-3
|View full text |Cite
|
Sign up to set email alerts
|

Survey-based forecast distributions for Euro Area growth and inflation: ensembles versus histograms

Abstract: Ensemble methods can be used to construct a forecast distribution from a collection of point forecasts. They are used extensively in meteorology, but have received little direct attention in economics. In a real-time analysis of the ECB's Survey of Professional Forecasters, we compare ensemble methods to histogrambased forecast distributions of GDP growth and inflation in the Euro Area. We find that ensembles perform very similarly to histograms, while being simpler to handle in practice. Given the wide availa… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

2
3
0

Year Published

2018
2018
2024
2024

Publication Types

Select...
7
1
1
1

Relationship

0
10

Authors

Journals

citations
Cited by 12 publications
(5 citation statements)
references
References 30 publications
2
3
0
Order By: Relevance
“…In these cases, forecasters overstate their ex ante uncertainty compared to the squared forecast errors and should, on average, reduce the variance of their histogram close to the target. Overall, these results square with similar evidence documented in Söderlind (2003, 2006) and Clements (2014Clements ( , 2018 for the FED-SPF and in Kenny et al (2014), Krüger (2017), andCasey (2021) for the ECB-SPF. In particular, our findings support the result of Clements (2014) that the ex ante uncertainty of SPF participants exceeds ex post uncertainty at short forecast horizons.…”
Section: Analysis Of Variance Misalignmentsupporting
confidence: 90%
“…In these cases, forecasters overstate their ex ante uncertainty compared to the squared forecast errors and should, on average, reduce the variance of their histogram close to the target. Overall, these results square with similar evidence documented in Söderlind (2003, 2006) and Clements (2014Clements ( , 2018 for the FED-SPF and in Kenny et al (2014), Krüger (2017), andCasey (2021) for the ECB-SPF. In particular, our findings support the result of Clements (2014) that the ex ante uncertainty of SPF participants exceeds ex post uncertainty at short forecast horizons.…”
Section: Analysis Of Variance Misalignmentsupporting
confidence: 90%
“…Many have sought -see Clements & Galvão (2017) and references therein -to compare model-based probability densities (or moments thereof) to the bin forecasts. Echoing our findings, Krüger (2017) reports similar forecast performances between histograms and distributions constructed from survey errors for the ECB's SPF. Recently, Bassetti et al (2022) Cakmakli & Demircan (2022) improve nowcasts from a factor model of US GDP by adding measurement equations for mean and variance factors that reflect the cross-sectional average and variance (i.e., disagreement) of individual SPF point forecasts.…”
Section: Introductionsupporting
confidence: 82%
“…We do not focus on these findings because they are not directly related to the analysis of the variance misalignment. 25…”
Section: Differences In Forecast Errorsmentioning
confidence: 99%