I would fit the data with various (r,p) arma models with the the desired garch assumption on the evolution of the variance and consider both the likelihood ratios and autocorrelation of the standardized residuals to determine the best model to fit the data. I have code for this if you want (although it is for multivariate problems and so is inefficient for univariariate garch.)
Dave Daan Taks wrote: > I have a question about my residuals. When testing for autocorrelation > I come to the conclusion that the models (garch, Egarch, GJR a.k.a. > Tarch) remove the correlation from the squared standardized residuals > but not from the standardized residuals. Are my models misspecified?? > I use returns from the FTSE, the DAX, and the S&P. These returns are > (heavily) correlated, should a garch model remove the correlation of > the returns? Or should it only remove the correlation of the squared > returns?? > Thanks. -- Dave Fournier, Otter Research Ltd PO Box 2040, Sidney, B.C. V8L 3S3, Canada 250-655-3364 email: [EMAIL PROTECTED] http://otter-rsch.com ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at http://jse.stat.ncsu.edu/ =================================================================