Does anything NOT beat the GARCH(1,1)?

In their paper on GARCH model comparison, Hansen and Lunde (2005) present evidence that among 330 different models, and using daily data on the DM/$ rate and IBM stock returns, no model does significantly better at predicting volatility (based on a … [Continue reading]

The GARCH-DCC Model and 2-stage DCC(MVT) estimation.

This short demonstration illustrates the use of the DCC model and its methods using the rmgarch package, and in particular an alternative method for 2-stage DCC estimation in the presence of the MVT distribution shape (nuisance) parameter. The … [Continue reading]

Rolling GARCH Forecasts

The rugarch package contains a rolling volatility forecast function called ugarchroll, but in this example I will show how easy it is to create a quick custom function. Having a rolling forecast of volatility can prove an invaluable indicator for use … [Continue reading]

How Good Are Your VaR Estimates?

Despite its shortcomings, Value at Risk (VaR) is still the most widely used measure for measuring the risk of a portfolio, and the preferred measure in the Basel II Accord. In this demonstration, I backtest a group of indices using a GARCH-DCC(MVT) … [Continue reading]

GARCH Parameter Uncertainty and Data Size

A frequently asked question relates to the minimum size of a dataset, required to obtain 'good' GARCH estimates. In this demonstration, the ugarchdistribution function is used to show how this question can be addressed within the rugarch package and … [Continue reading]