Nowcasting in a Pandemic using Non-Parametric Mixed Frequency VARs
Econometrics
2020-12-02 v3 Applications
Machine Learning
Abstract
This paper develops Bayesian econometric methods for posterior inference in non-parametric mixed frequency VARs using additive regression trees. We argue that regression tree models are ideally suited for macroeconomic nowcasting in the face of extreme observations, for instance those produced by the COVID-19 pandemic of 2020. This is due to their flexibility and ability to model outliers. In an application involving four major euro area countries, we find substantial improvements in nowcasting performance relative to a linear mixed frequency VAR.
Cite
@article{arxiv.2008.12706,
title = {Nowcasting in a Pandemic using Non-Parametric Mixed Frequency VARs},
author = {Florian Huber and Gary Koop and Luca Onorante and Michael Pfarrhofer and Josef Schreiner},
journal= {arXiv preprint arXiv:2008.12706},
year = {2020}
}
Comments
JEL: C11, C32, C53, E37; Keywords: Regression tree models, Bayesian, macroeconomic forecasting, vector autoregressions