Measuring multiple monetary policy shocks based on heteroscedasticity
We propose a two-step approach to estimate multiple monetary policy shocks and their causal effects based on daily financial market data and policy events. First, we combine a heteroscedasticity-based identification scheme with recursive zero restrictions along the term structure of interest rates to disentangle multiple dimensions of monetary policy shocks.
We derive an IV estimator that allows us to recursively estimate multi-dimensional causal effects at a daily frequency. Second, we exploit the cross-sectional heterogeneity of the impact effect on various financial market variables to predict the underlying unobserved monetary policy shocks. The heteroscedasticity-based monetary policy shocks have similar effects on financial and macroeconomic variables as those based on high-frequency identification. The weak instrument problem, which is often encountered when using high-frequency surprises in low-frequency macroeconomic models, is significantly less pronounced.