[R-SIG-Finance] Is it possible to import residuals of mean.model into variance.model in rugarch package or others?
alexios at 4dscape.com
Wed Dec 26 09:13:24 CET 2012
1. Estimate your conditional mean equation in a first stage (separately).
2. Pass the residuals from your model as the data in 'ugarchfit', having
set 'ugarchspec' to have (0,0) 'armaOrder' and 'include.mean' set to
FALSE. Pass any "external" variables for the GARCH model in the
'external.regressors' slot in the ugarchspec variance.model list
(appropriately lagged and in the form of a matrix). Provide some
starting values for the regressors parameters ('setstart<-') and
preferably define their upper and lower bounds (use 'setbounds<-' method
on the spec - this is available starting from version 1.0-14).
On 26/12/2012 07:14, SamuelS wrote:
> I try to build up a GARCH model in which i want to multiply pre-lagged
> squared residuals of mean.model(RES(-1)^2) and several dummy variables(Fi,
> i=1,2,3,…) and use the product RES(-1)^2*Fi as a variable in variance.model,
> similar to but different from 'gjrGARCH'.
> I am learning and trying to use the rugarch package to fit the model, but
> it seems that the spec function can not contain a unknown variable RES(-1),
> the residuals of mean.model. Then I checked vignette(bottom of page4) and
> found "the mean and variance equations in the maximization of the likelihood
> is carried out jointly in a single step" insteading of 2-step method. Does
> it imply it is impossible to use residuals of mean.model as a variable or
> part of a variable in variance.model in rugarch package?
> Please let me know if there is a solution by using rugarch package or
> other packages. Thanks a lot.
> Best regards,
> View this message in context: http://r.789695.n4.nabble.com/Is-it-possible-to-import-residuals-of-mean-model-into-variance-model-in-rugarch-package-or-others-tp4653934.html
> Sent from the Rmetrics mailing list archive at Nabble.com.
> R-SIG-Finance at r-project.org mailing list
> -- Subscriber-posting only. If you want to post, subscribe first.
> -- Also note that this is not the r-help list where general R questions should go.
More information about the R-SIG-Finance