If positive and negative shocks of equal magnitude asymmetrically contribute to volatility, then you can model the innovations process using an EGARCH model and include leverage effects. For details on how to model volatility clustering using an EGARCH model, see egarch.
||EGARCH conditional variance time series model|
Create various EGARCH models.
Change modifiable model properties using dot notation.
Specify Gaussian or t distributed innovations process.
Create a conditional variance model for daily Deutschmark/British pound foreign exchange rates.
Create a composite conditional mean and variance model.
Estimate a composite conditional mean and variance model.
Infer conditional variances from a fitted conditional variance model.
Fit two competing, conditional variance models to data, and then compare their fits using a likelihood ratio test.
Compare the fits of several conditional variance models using AIC and BIC.
Forecast the Deutschmark/British pound foreign exchange rate using a fitted conditional variance model.
Forecast responses and conditional variances from a composite conditional mean and variance model.
Compare simulation-based forecasts to MMSE forecasts to assess bias.
Learn about models that account for volatility clustering.
Learn how maximum likelihood is carried out for conditional variance models.
Constrain the model during estimation using known parameter values.
Specify presample data to initialize the model.
Specify initial parameter values for estimation.
Troubleshoot estimation issues by specifying alternative optimization options.
Learn about Monte Carlo simulation.
Learn about presample requirements for simulation.
Learn about Monte Carlo forecasting.
Learn about MMSE forecasting.