Conventional and unconventional monetary policy rate uncertainty and stock market volatility : a forecasting perspective

Abstract

Theory suggests the existence of a bi-directional relationship between stock market volatility and monetary policy rate uncertainty. In light of this, we forecast volatilities of equity markets and shadow short rates (SSR) – a common metric of both conventional and unconventional monetary policy decisions, by applying a bivariate Markov-switching multifractal (MSM) model. Using daily data of eight advanced economies (Australia, Canada, Euro area, Japan, New Zealand, Switzerland, the UK, and the US) over the period of January 1995 to February 2025, we find that the bivariate MSM model outperforms, in a statistically significant manner, not only the benchmark historical volatility and the univariate MSM models, but also the Dynamic Conditional Correlation Generalized Autoregressive Conditional Heteroskedasticity (DCC-GARCH) framework, particularly at longer forecast horizons. Our findings are robust to different out-of-sample periods, and superiority of the bivariate MSM is also confirmed relative to the corresponding Generalized Autoregressive Score (GAS) model. This finding confirms the bi-directional relationship between stock market volatility and uncertainty surrounding conventional and unconventional monetary policies, which in turn has important implications for academics, investors and policymakers.