Menu

Dynamic Conditional Correlation (DCC) GARCH Model

Advanced multivariate volatility model for portfolio analysis

Model Configuration

For optimal performance, we recommend 2-5 assets.

No analysis results yet

Select at least 2 tickers and click "Run DCC-GARCH Model" to start.

Running a multivariate model may take up to a minute.

About the DCC-GARCH Model

The Dynamic Conditional Correlation GARCH (DCC-GARCH) model, introduced by Engle (2002), extends univariate GARCH models to a multivariate setting by allowing for time-varying correlations between assets.

Model Structure

The DCC-GARCH model is a two-step approach:

  1. Univariate GARCH: Each asset's volatility is modeled independently using standard GARCH models.
  2. Dynamic Correlation: The correlations between standardized residuals are modeled using a separate dynamic process.

The conditional covariance matrix Ht is decomposed as:

Ht = DtRtDt

Where:

  • Dt is a diagonal matrix of volatilities from univariate GARCH models
  • Rt is the time-varying correlation matrix