Monetary policy and financial stress: a multi-method causal analysis

This paper investigates the relationship between monetary policy and financial stress by distinguishing informational effects from conventional policy transmission. Using Ordinary Least Squares (OLS) with monetary policy shock decomposition, Double Machine Learning (DML), and Bayesian Structural Time Series (BSTS) methods, we examine how monetary policy affects the US Financial Stress Index. The results reveal a significant negative relationship between monetary policy shocks and financial stress, largely driven by central bank information shocks rather than pure monetary policy shocks. DML estimates confirm the robustness of this finding after accounting for nonlinear macro-financial interactions. BSTS counterfactual analysis indicates that financial stress remained persistently above its no-tightening trajectory during the post-2022 tightening cycle, suggesting that sustained monetary tightening contributed to elevated financial stress over time. Rolling-window regressions further reveal substantial regime dependence in the monetary policy – financial stress relationship.