A Nonparametric Approach to Augmenting a Bayesian VAR with Nonlinear Factors

2025-08-19

AI Summary

Traditional linear Bayesian VAR models suffer from functional misspecification, leading to model failure. To address this, we propose a nonparametrically enhanced Bayesian VAR model. Methodologically, the approach integrates regression trees, Bayesian factor analysis, and MCMC inference, enabling equation-by-equation estimation and efficient Bayesian computation. Its core innovation lies in incorporating tree-based nonlinear factors—via functional pooling—to flexibly capture complex nonlinear dynamics among high-dimensional macroeconomic variables, while preserving compatibility with existing linear factor identification frameworks and naturally extending to nonlinear structural identification. Empirical evaluation on both synthetic and real-world macroeconomic datasets demonstrates substantial improvements in forecasting accuracy and robust structural interpretability, particularly for high-dimensional, strongly nonlinear economic systems.

Technology Category

• Machine Learning: Bayesian Learning
• Reasoning under Uncertainty: Relational Probabilistic Models
• Game Theory and Economic Paradigms: Behavioral Game Theory

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Sustainability of Web economics

Abstract

This paper proposes a Vector Autoregression augmented with nonlinear factors that are modeled nonparametrically using regression trees. There are four main advantages of our model. First, modeling potential nonlinearities nonparametrically lessens the risk of mis-specification. Second, the use of factor methods ensures that departures from linearity are modeled parsimoniously. In particular, they exhibit functional pooling where a small number of nonlinear factors are used to model common nonlinearities across variables. Third, Bayesian computation using MCMC is straightforward even in very high dimensional models, allowing for efficient, equation by equation estimation, thus avoiding computational bottlenecks that arise in popular alternatives such as the time varying parameter VAR. Fourth, existing methods for identifying structural economic shocks in linear factor models can be adapted for the nonlinear case in a straightforward fashion using our model. Exercises involving artificial and macroeconomic data illustrate the properties of our model and its usefulness for forecasting and structural economic analysis.

Problem

• Modeling nonlinear factors nonparametrically to avoid specification errors
• Enabling efficient Bayesian computation in high-dimensional nonlinear VAR systems
• Adapting structural shock identification methods for nonlinear factor models

Innovation

• Nonparametric regression trees for nonlinear factors
• Bayesian MCMC computation enabling efficient estimation
• Adaptable structural shock identification in nonlinear models