Let the Tree Decide: FABART A Non-Parametric Factor Model

TL;DR

This paper introduces FABART, a nonparametric factor model that combines Bayesian Additive Regression Trees with FAVAR to improve macro-financial forecasting and analyze oil price shock asymmetries, capturing complex nonlinearities.

Contribution

It develops a novel nonparametric framework integrating BART into FAVAR, enhancing nonlinear relationship modeling and forecast accuracy in macro-financial data.

Findings

FABART outperforms linear models in forecasting industrial production.

The model uncovers significant asymmetries in oil shock transmission.

FABART remains consistent under linear data-generating processes.

Abstract

This article proposes a novel framework that integrates Bayesian Additive Regression Trees (BART) into a Factor-Augmented Vector Autoregressive (FAVAR) model to forecast macro-financial variables and examine asymmetries in the transmission of oil price shocks. By employing nonparametric techniques for dimension reduction, the model captures complex, nonlinear relationships between observables and latent factors that are often missed by linear approaches. A simulation experiment comparing FABART to linear alternatives and a Monte Carlo experiment demonstrate that the framework accurately recovers the relationship between latent factors and observables in the presence of nonlinearities, while remaining consistent under linear data-generating processes. The empirical application shows that FABART substantially improves forecast accuracy for industrial production relative to linear benchmarks, particularly during periods of heightened volatility and economic stress. In addition, the model reveals pronounced sign asymmetries in the transmission of oil supply news shocks to the U.S. economy, with positive shocks generating stronger and more persistent contractions in real activity and inflation than the expansions triggered by negative shocks. A similar pattern emerges at the U.S. federal state level, where negative shocks lead to modest declines in employment compared to the substantially larger contractions observed after positive shocks.