Should I stay or should I go? A latent threshold approach to large-scale mixture innovation models

TL;DR

This paper introduces a computationally efficient latent threshold algorithm for large-scale TVP-VARs with mixture innovations, improving forecasting and understanding of macroeconomic and financial data.

Contribution

It develops a novel latent threshold approach that simplifies inference in large TVP-VARs with mixture components, reducing computational complexity.

Findings

Improved forecast accuracy for US interest rates.

Evidence of time-varying effects of monetary policy.

Enhanced computational efficiency in large models.

Abstract

This paper proposes a straightforward algorithm to carry out inference in large time-varying parameter vector autoregressions (TVP-VARs) with mixture innovation components for each coefficient in the system. We significantly decrease the computational burden by approximating the latent indicators that drive the time-variation in the coefficients with a latent threshold process that depends on the absolute size of the shocks. The merits of our approach are illustrated with two applications. First, we forecast the US term structure of interest rates and demonstrate forecast gains of the proposed mixture innovation model relative to other benchmark models. Second, we apply our approach to US macroeconomic data and find significant evidence for time-varying effects of a monetary policy tightening.