DCC-MIDAS
Dynamic Conditional Correlation MIDAS · Also known as: DCC mixed-frequency model
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.
Read the full method
Sign in with a free account to read this section.
Method map
The neighbourhood of related methods — select a node to explore.
When to use it
Use DCC-MIDAS when managing portfolios and macro conditions affect diversification benefits, when valuing options dependent on multiple assets, or when studying how macro shocks transmit via correlation changes. Valuable for asset allocators, risk managers, and macro-finance researchers.
Strengths & limitations
- Flexibly incorporates mixed-frequency information for correlation forecasting
- Captures macro drivers of asset correlations without losing high-frequency detail
- Parsimonious relative to multivariate GARCH models
- Naturally handles unbalanced data (different release schedules)
- Requires careful specification of macro predictors; misspecification biases results
- Estimation is computationally intensive; convergence can be challenging
- Limited to capturing linear macro-correlation relationships
- Macro lag selection is ad hoc; results sensitive to specification
Frequently asked
Which macro variables should I include?
Theory-driven selection: inflation for stock-bond correlations, credit spreads for equity-credit linkages, growth expectations for broad diversification. Test individual and joint significance; avoid data mining.
How do I handle macro data release lags?
Align by publication date, not reference date. If monthly unemployment releases on the 7th, use it from that date forward in correlations. Avoid look-ahead bias.
Can I use real-time macro data?
Yes, but be careful of revisions. Real-time data initially released differs from final; model revisions explicitly or use final-revised data with realistic lag.
How do I forecast correlations with DCC-MIDAS?
Forecast macro variables (using VAR or other models), plug into the MIDAS correlation equation. The forecast horizon for correlations depends on macro forecast horizon.
Sources
- Engle, R. F., Ghysels, E., & Sohn, B. (2013). Stock market volatility and macroeconomic fundamentals. Review of Economics and Statistics, 95(3), 776-797. DOI: 10.1162/rest_a_00300 ↗
- Colacito, R., Engle, R. F., & Ghysels, E. (2011). A component model for dynamic correlations. Journal of Econometrics, 164(1), 45-59. DOI: 10.1016/j.jeconom.2011.02.013 ↗
How to cite this page
ScholarGate. (2026, June 3). Dynamic Conditional Correlation MIDAS. ScholarGate. https://scholargate.app/en/econometrics/dcc-midas
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
- Component GARCHEconometrics↔ compare
- GARCH-MIDASEconometrics↔ compare
- Quantile VAREconometrics↔ compare