Subspace shrinkage in conjugate Bayesian vector autoregressions

Bibliographic Data

ID21653236
AuthorsFlorian Huber (0000-0002-2896-7921, University of Salzburg Salzburg Austria, corresponding author), Gary Koop (0000-0002-6091-378X, University of Strathclyde Glasgow UK)
Year2023
Volume38
Issue4
Pages556-576
Publication date2023-06-01
Open AccessYes
TypeARTICLE
VenueJournal of Applied Econometrics (JOURNAL)
Journal identifiersISSN: 1099-1255 • E-ISSN: 0883-7252
PublisherWiley (PUBLISHER • GB)
DOI10.1002/jae.2966
PMID38505535
OpenAlexW3184784571
LanguageEN
Citations received1
References cited29

Macroeconomists using large datasets often face the choice of working with either a large vector autoregression (VAR) or a factor model. In this paper, we develop a conjugate Bayesian VAR with a subspace shrinkage prior that combines the two. This prior shrinks towards the subspace which is defined by a factor model. Our approach allows for estimating the strength of the shrinkage and the number of factors. After establishing the theoretical properties of our prior, we show that it successfully detects the number of factors in simulations and that it leads to forecast improvements using US macroeconomic data

Bayesian inference · Bayesian probability · Bayesian vector autoregression · Econometrics · Factor analysis · Machine learning · Shrinkage · Shrinkage estimator · Statistics · Subspace topology · Vector autoregression · Computer Science · Italy: Economic History and Contemporary Issues · Market Dynamics and Volatility · Mathematics · Monetary Policy and Economic Impact · Artificial Intelligence

Tools

Open DOIOpen Access