Structural changes in asset correlations and macroeconomic fundamentals

Abstract

This article proposes a novel approach to modelling structural changes in asset returns correlations and their relationship to macroeconomic fundamentals. We introduce a new correlation component model, the Regime-switching DCC-MIDAS, that incorporates breaks of different type in the conditional and unconditional correlations. Breaks in the secular component are associated with low-frequency macroeconomic fundamentals via a Smooth Transition mixed-data sampling regression, while short-run correlations are characterized by abrupt regime switches linked to market constraints. Following a discussion of estimation, inference and simulation-based evaluations, the model is applied to the prediction of future energy returns. The results indicate that the Regime-switching DCC-MIDAS is a very useful specification especially in periods of intense market instability, such as the recent pandemic crisis.

Keywords: Mixed frequency data, structural breaks, correlation component models, risk management

JEL Classification: C01, C51, C52, C53, C58