I have made the same notification.
In the case of Asymmetric power ARCH (APARCH), garchFit and garchOxFit commands
give remarkably different results. Instead of that with normal garch model, the
results are exactly same. So, there must be some mistake in the garchFit
commands.
Best regards,
Allan Pe
Researcher
> Date: Wed, 12 Dec 2007 18:07:34 +0200
> From: veleinon@mail.student.oulu.fi
> To: r-devel@r-project.org
> Subject: [Rd] APARCH
>
>
> Hi,
>
> Could somebody say if it is possible to compute APARCH-models with garchFit
> commands.
>
> I have earlier used aaa (garchOxFit) and now I try to use bbb (look below)
>
> aaa <-
>
garchOxFit(formula.mean=~arma(1,0),formula.var=~aparch(1,1),series=nyk,cond.dist=c('gaussian'))
>
>
> bbb <- garchFit(formula=~arma(1,0)+aparch(1,1),data=nyk)
>
> aaa works well, but I need other characteristics of garchFit and, therefore
it
> would be important to know what's wrong with my bbb command (the value
of delta
> is fixed to 2 and I get totally different coefficients than with aaa).
>
> How should I write bbb to get similar answer than with aaa?
>
> Thanks a lot,
>
> Veikko
>
> ______________________________________________
> R-devel@r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-devel
_________________________________________________________________
Joululahjaksi joukko uusia ja ilmaisia Windows Live palveluja!
http://get.live.com
[[alternative HTML version deleted]]