Forecasting aggregate market volatility: The role of good and bad uncertainties

We decompose economic uncertainty into good and bad components according to the sign of innovations. Our results indicate that bad uncertainty provides stronger predictive content regarding future market volatility than good uncertainty. The asymmetric models with good and bad uncertainties forecast market volatility in a better way than the symmetric models with overall uncertainty. The combination for asymmetric uncertainty models significantly outperforms the benchmark of autoregression, as well as the combination for symmetric models. The revealed volatility predictability is further demonstrated to be economically significant in the framework of portfolio allocation.

Automated summary

The research shows that bad economic uncertainty has stronger predictive power for future market volatility than good uncertainty. Asymmetric models outperform symmetric models in forecasting market volatility and have economic significance in portfolio allocation.