[R-SIG-Finance] ugarchforecast

[alexios ghalanos]

I really don't understand what you mean about the eGARCH model.
See the comparison against the Bollerslev-Ghysels published benchmark
by running the benchmarking code:
ugarchbench( benchmark = "published" )

Also, I do not benchmark against S-PLUS nor do I consider it to be the 
standard for benchmarking of GARCH models. The code in rugarch is open 
source so feel free to look under the hood and decide on whether it 
meets, or not, your requirements.

-Alexios

On 27/05/2012 16:40, Johanna Slomp wrote:
> it works thanks!!
> for the egarch, i have doubt if it work as the model used in S-plus, in
> the book it is defined as an alternative model, if the model is just
> like in the manual every explanaition is like in the books!
> thanks again
> Jo
>
> 2012/5/27 alexios ghalanos <alexios at 4dscape.com
> <mailto:alexios at 4dscape.com>>
>
>     1. unname(as.numeric(share1))
>     2. What more information do you want than is in the vignette?
>     The formula for calculating EGARCH is clearly defined.
>
>     -Alexios
>
>
>     On 27/05/2012 16:05, Johanna Slomp wrote:
>
>         1. thanks for the reply, the file is a matrix 1x1000. How I pass
>         it as
>         an unnamed numeric vector? should I specify it in the routine?
>         2. Does exist another manual different than Introduction to rugarch
>         package version 1.0-8? I would like to have more information
>         about the
>         egarch formula and parameters (model form used in R).
>         Thanks
>         Jo
>
>         2012/5/27 alexios ghalanos <alexios at 4dscape.com
>         <mailto:alexios at 4dscape.com>
>         <mailto:alexios at 4dscape.com <mailto:alexios at 4dscape.com>>>
>
>
>             Since you've not said what the class of share1 is
>         ('class(share1)'),
>             your best bet is to pass the "share1" as an unnamed numeric
>         vector
>             to the fit routine.
>             -Alexios
>
>
>             On 27/05/2012 15:21, Johanna Slomp wrote:
>
>                 Hi R users
>                 I have some problems getting the t+1 variance using
>         rugarch package
>                 the simplest model is:
>
>                 spec1<-
>
>           ugarchspec(variance.model=____list(model="sGARCH",____garchOrder=c(1,1),submodel=____NULL),
>                 mean.model=list(armaOrder=c(0,____0)),
>         distribution.model="norm")
>                 fit1<- ugarchfit(data=share1,spec=____spec1)
>
>                 sgarch.pred2 = ugarchforecast(fit1, n.ahead = 1)
>
>                   the forecast gives me the error:
>
>                 *Errore in format.default(*
>
>                 *Dates[n], "%m/%d/%y") :
>                    argomento 'trim' non valido*
>
>
>
>
>                 The file share1 have just the daily log return of a share.
>
>                 How can i fix it?
>
>                 Regards
>
>                 Jo
>
>                         [[alternative HTML version deleted]]
>
>                 ___________________________________________________
>         R-SIG-Finance at r-project.org <mailto:R-SIG-Finance at r-project.org>
>         <mailto:R-SIG-Finance at r-__project.org
>         <mailto:R-SIG-Finance at r-project.org>>
>                 mailing list
>         https://stat.ethz.ch/mailman/____listinfo/r-sig-finance
>         <https://stat.ethz.ch/mailman/__listinfo/r-sig-finance>
>
>         <https://stat.ethz.ch/mailman/__listinfo/r-sig-finance
>         <https://stat.ethz.ch/mailman/listinfo/r-sig-finance>>
>                 -- 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.
>
>
>
>
>