Sophisticated and small versus simple and sizeable: When does it pay off to introduce drifting coefficients in Bayesian VARs?

TL;DR

This paper investigates when complex Bayesian VAR models with drifting coefficients outperform simpler models, finding that complexity pays off in small datasets, while simpler models excel with larger data, and proposes shrinkage priors and dynamic model selection to optimize forecasting.

Contribution

It introduces novel shrinkage priors for Bayesian VARs and explores dynamic model selection to enhance forecasting performance across different data sizes.

Findings

Drifting coefficients improve forecasts in small datasets.

Simpler models perform better with large datasets.

Shrinkage priors help mitigate dimensionality issues.

Abstract

We assess the relationship between model size and complexity in the time-varying parameter VAR framework via thorough predictive exercises for the Euro Area, the United Kingdom and the United States. It turns out that sophisticated dynamics through drifting coefficients are important in small data sets, while simpler models tend to perform better in sizeable data sets. To combine the best of both worlds, novel shrinkage priors help to mitigate the curse of dimensionality, resulting in competitive forecasts for all scenarios considered. Furthermore, we discuss dynamic model selection to improve upon the best performing individual model for each point in time.