Abstract:
This paper predicts the daily return volatility of 28 advanced and developing stock markets using monthly metrics of the corresponding country and global energy-related uncertainty indexes (EUIs) recently proposed in the literature. Using data in their “natural” frequencies to avoid aggregation bias, the results show that country-specific and global EUIs have predictive powers for stock returns volatility for the in-sample periods, with increased levels of EUIs exhibiting the tendency to heighten volatility. This predictability also withstands various out-of-sample forecast horizons, implying that EUI is a statistically relevant predictor in the out-of-sample analysis. The forecast precision of the GARCH-MIDAS model is improved by incorporating global EUIs relatively more than country-specific EUIs. The robustness of the findings with respect to the choice of EUI and sample definition is further confirmed. The outcomes have important policy implications for the concerned stakeholders who are concerned with stability in the global financial system and economy.
