How Sensitive are VAR Forecasts to Prior Hyperparameters? An Automated Sensitivity Analysis

Chan, J; Jacobi, L; Zhu, D

How Sensitive are VAR Forecasts to Prior Hyperparameters? An Automated Sensitivity Analysis

Chan, J

Jacobi, L Zhu, D

Permalink

Publisher:: Jai Press Inc.
Publication Type:: Journal Article
Citation:: Advances in Econometrics, 2019, 40A pp. 229 - 248
Issue Date:: 2019-07-01

Closed Access

	Filename	Description	Size
	AD_VAR_sub2.pdf	Accepted Manuscript Version	472.21 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Chan, J https://orcid.org/0000-0003-3632-128X	en_US
dc.contributor.author	Jacobi, L	en_US
dc.contributor.author	Zhu, D	en_US
dc.date.accessioned	2020-04-03T21:46:14Z
dc.date.available	2020-04-03T21:46:14Z
dc.date.issued	2019-07-01	en_US
dc.identifier.citation	Advances in Econometrics, 2019, 40A pp. 229 - 248	en_US
dc.identifier.issn	0731-9053	en_US
dc.identifier.uri	http://hdl.handle.net/10453/139794
dc.description.abstract	Vector autoregressions (VAR) combined with Minnesota-type priors are widely used for macroeconomic forecasting. The fact that strong but sensible priors can substantially improve forecast performance implies VAR forecasts are sensitive to prior hyperparameters. But the nature of this sensitivity is seldom investigated. We develop a general method based on Automatic Differentiation to systematically compute the sensitivities of forecasts – both points and intervals – with respect to any prior hyperparameters. In a forecasting exercise using US data, we find that forecasts are relatively sensitive to the strength of shrinkage for the VAR coefficients, but they are not much affected by the prior mean of the error covariance matrix or the strength of shrinkage for the intercepts.	en_US
dc.language	en	en_US
dc.publisher	Jai Press Inc.	en_US
dc.relation.ispartof	Advances in Econometrics	en_US
dc.relation.isbasedon	10.1108/S0731-90532019000040A010	en_US
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject.classification	Econometrics	en_US
dc.title	How Sensitive are VAR Forecasts to Prior Hyperparameters? An Automated Sensitivity Analysis	en_US
dc.type	Journal Article
utslib.citation.volume	40A	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Business
pubs.organisational-group	/University of Technology Sydney/Faculty of Business/Economics Discipline
utslib.copyright.status	closed_access	*
pubs.consider-herdc	true	en_US
pubs.publication-status	Accepted	en_US
pubs.volume	40A	en_US

Abstract:

Vector autoregressions (VAR) combined with Minnesota-type priors are widely used for macroeconomic forecasting. The fact that strong but sensible priors can substantially improve forecast performance implies VAR forecasts are sensitive to prior hyperparameters. But the nature of this sensitivity is seldom investigated. We develop a general method based on Automatic Differentiation to systematically compute the sensitivities of forecasts – both points and intervals – with respect to any prior hyperparameters. In a forecasting exercise using US data, we find that forecasts are relatively sensitive to the strength of shrinkage for the VAR coefficients, but they are not much affected by the prior mean of the error covariance matrix or the strength of shrinkage for the intercepts.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/139794