方法对比

	GARCH-MIDAS	DCC-MIDAS	无约束MIDAS回归
领域	计量经济学	计量经济学	计量经济学
方法族	Regression model	Regression model	Regression model
起源年份	2012	2013	2007
提出者	Engle and Ghysels	Engle, Ghysels, and Sohn	Eric Ghysels
类型	Time-varying variance model	Time-varying correlation model	Time-series regression
开创性文献	Engle, R. F., & Ghysels, E. (2012). GARCH for long memory. Journal of Econometrics, 164(2), 385-391.	Engle, R. F., Ghysels, E., & Sohn, B. (2013). Stock market volatility and macroeconomic fundamentals. Review of Economics and Statistics, 95(3), 776-797.	Foroni, C., Ghysels, E., & Marcellino, M. (2015). Mixed-frequency vector autoregressive models. International Journal of Forecasting, 31(4), 1051-1070.
别名	Mixed-frequency volatility model	DCC mixed-frequency model	Unrestricted Mixed Data Sampling
相关	3	3	3
摘要	GARCH-MIDAS decomposes volatility into short-term (GARCH) and long-term (MIDAS) components, allowing low-frequency macroeconomic variables to drive medium-term volatility while high-frequency returns govern daily fluctuations. Introduced by Engle and Ghysels (2012), this framework elegantly separates volatility time scales. The approach is powerful for understanding how macro conditions (growth, inflation) drive risk premia and for improved volatility forecasting.	DCC-MIDAS combines dynamic conditional correlation (DCC) GARCH with mixed-frequency data sampling (MIDAS), enabling estimation of time-varying correlations between variables when observations arrive at different frequencies. Introduced by Engle et al. (2013), it models how correlations evolve with low-frequency macroeconomic conditions using high-frequency asset price information. This is crucial for portfolio risk management and understanding macro-finance linkages.	U-MIDAS (Unrestricted MIDAS) is a regression framework designed to handle mixed-frequency data—when explanatory variables arrive at different sampling frequencies (e.g., monthly GDP mixed with daily stock returns). Introduced by Ghysels and colleagues (2007), it eliminates the restrictive lag-structure polynomial constraints of the original MIDAS approach, allowing fuller use of high-frequency information. This flexibility makes it ideal for nowcasting and real-time economic forecasting.