Tail Forecasting with Multivariate Bayesian Additive Regression Trees
- Author(s)
- Todd E. Clark, Florian Huber, Gary Koop, Massimiliano Marcellino, Michael Pfarrhofer
- Abstract
We develop multivariate time-series models using Bayesian additive regression trees that posit nonlinearities among macroeconomic variables, their lags, and possibly their lagged errors. The error variances can be stable, feature stochastic volatility, or follow a nonparametric specification. We evaluate density and tail forecast performance for a set of U.S. macroeconomic and financial indicators. Our results suggest that the proposed models improve forecast accuracy both overall and in the tails. Another finding is that when allowing for nonlinearities in the conditional mean, heteroskedasticity becomes less important. A scenario analysis reveals nonlinear relations between predictive distributions and financial conditions.
- Organisation(s)
- Department of Economics
- External organisation(s)
- Federal Reserve Bank of Cleveland, Università Commerciale Luigi Bocconi, Paris-Lodron Universität Salzburg, University of Strathclyde
- Journal
- International Economic Review
- Volume
- 64
- Pages
- 979-1022
- No. of pages
- 44
- ISSN
- 0020-6598
- DOI
- https://doi.org/10.1111/iere.12619
- Publication date
- 12-2022
- Peer reviewed
- Yes
- Austrian Fields of Science 2012
- 502025 Econometrics, 502018 Macroeconomics
- Keywords
- ASJC Scopus subject areas
- Economics and Econometrics
- Portal url
- https://ucrisportal.univie.ac.at/en/publications/5720761d-75a0-496a-9595-f50fd391e05c