This paper proposes a mixed-frequency stochastic volatility model for intraday returns that captures fast and slow level shifts in the volatility level induced by news from both low-frequency
variables and scheduled announcements. A MIDAS component describes slow-moving changes in volatility driven by daily variables, while an announcement component captures fast event-driven volatility bursts. Using 5-minute crude oil futures returns, we show that accounting for both fast and slow level shifts significantly improves volatility forecasts at intraday and daily horizons. The superior forecasts also translate into higher Sharpe ratios using the volatility-managed portfolio strategy.
Comissão Organizadora
Comissão Científica