MIDAS volatility forecast performance under market stress: Evidence from emerging stock markets

This paper evaluates weekly out-of-sample volatility forecast performance of univariate Mixed Data Sampling (MIDAS) model compared to the benchmark model of GARCH(1,1) for ten emerging stock markets. The results show that the MIDAS model offers a statistically better forecasting precision during the recent financially turbulent era, based on the test suggested by West (2006). For the tranquil period, however, the MIDAS model cannot produce a statistically better weekly volatility forecast. ► We assess out-of-sample volatility forecasting performance of the Mixed Data Sampling (MIDAS) model. ► The MIDAS model offers statistically better forecasting precision for highly volatile periods. ► This finding is mainly due to MIDAS’ ability to exploit fluctuations in higher frequency data. ► The results suggest fruitful implications for stress testing, option pricing, and trading options.