Research Repository

Bayesian Compressed Vector Autoregressions

Koop, G and Korobilis, D and Pettenuzzo, D (2018) 'Bayesian Compressed Vector Autoregressions.' Journal of Econometrics. ISSN 0304-4076

[img] Text
SSRN-id2754241.pdf - Accepted Version
Restricted to Repository staff only until 12 November 2020.
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (844kB) | Request a copy


Macroeconomists are increasingly working with large Vector Autoregressions (VARs) where the number of parameters vastly exceeds the number of observations. Existing approaches either involve prior shrinkage or the use of factor methods. In this paper, we develop an alternative based on ideas from the compressed regression literature. It involves randomly compressing the explanatory variables prior to analysis. A huge dimensional problem is thus turned into a much smaller, more computationally tractable one. Bayesian model averaging can be done over various compressions, attaching greater weight to compressions which forecast well. In a macroeconomic application involving up to 129 variables, we find compressed VAR methods to forecast better than either factor methods or large VAR methods involving prior shrinkage.

Item Type: Article
Uncontrolled Keywords: multivariate time series, random projection, forecasting
Subjects: H Social Sciences > HA Statistics
H Social Sciences > HB Economic Theory
Divisions: Faculty of Social Sciences > Essex Business School > Essex Finance Centre
Depositing User: Elements
Date Deposited: 18 Jan 2018 10:54
Last Modified: 07 Aug 2019 21:15

Actions (login required)

View Item View Item