Data-based priors for vector error correction models?

We propose two data-based priors for vector error correction models. Both priors lead to highly automatic approaches which require only minimal user input. For the first one, we propose a reduced rank prior which encourages shrinkage towards a low-rank, row-sparse, and column-sparse long-run matrix. For the second one, we propose the use of the horseshoe prior, which shrinks all elements of the long-run matrix towards zero. Two empirical investigations reveal that Bayesian vector error correction (BVEC) models equipped with our proposed priors scale well to higher dimensions and forecast well. In comparison to VARs in first differences, they are able to exploit the information in the level variables. This turns out to be relevant to improve the forecasts for some macroeconomic variables. A simulation study shows that the BVEC with data-based priors possesses good frequentist estimation properties.(c) 2021 International Institute of Forecasters. Published by Elsevier B.V. All rights reserved.

Automated summary

This paper proposes two data-based priors for vector error correction models, which require minimal user input and have automatic approaches. The first prior encourages shrinkage towards a low-rank, row-sparse, and column-sparse long-run matrix, while the second prior shrinks all elements of the long-run matrix towards zero using the horseshoe prior. Empirical investigations show that Bayesian vector error correction models equipped with these priors perform well in higher dimensions and forecasting. Compared to VARs in first differences, they effectively exploit the information in level variables and improve forecasts for some macroeconomic variables. A simulation study demonstrates that the BVEC with data-based priors has good frequentist estimation properties.