The Unconditional Covariance Matrix in DCC GARCH

Summary

The document asks what the unconditional covariance matrix represents in a Dynamic Conditional Correlation GARCH model. The question contrasts a data-based covariance matrix for two series, built from their individual variances and their covariance, with the model quantity commonly written as Q-bar.

The answer identifies Q-bar as the covariance between the error terms for pairs of assets, with each error term indexed by its asset. This clarifies which model quantities the matrix relates, but the exchange provides only a brief definition. It does not explain how Q-bar is estimated, how it enters the DCC recursion, or how it differs in practice from a sample covariance matrix of raw returns. Those details would be needed for a fuller account of model implementation.

Key ideas

• In DCC GARCH, Q-bar denotes unconditional covariance among asset-specific error terms.
• The matrix entries pair error terms associated with different assets.
• The brief explanation does not describe estimation or the matrix's role in the DCC recursion.

Tags

# Explain the unconditional covariance in Dynamic Conditional correlation( DCC ) GARCH model


# Explain the unconditional covariance in Dynamic Conditional correlation( DCC ) GARCH model












Confused about the unconditional covariance matrix in a DCC GARCH model. Could anyone help me understand it? My understanding is that we get the unconditional covariance before based on the data sets. For example, two data sets, A and B, then the unconditional covariance matrix is built by the variance of A and B respectively and covariance of them, is that true? Thanks.

## Answer by xxx (score 0, accepted)

https://quant.stackexchange.com/a/17319

Your question is about the $\overline{Q}$, right?

If so, it is the covariance between the error terms $E_{i,t}$ and $E_{j,t}$.(The sub term $i$ comes from asset $i$, and $j$ for asset $j$)

Shown in full with attribution under the source's licence. Licence: CC BY-SA 4.0 (Stack Exchange)

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.