VARMA

classic Classic list List threaded Threaded
3 messages Options
Reply | Threaded
Open this post in threaded view
|

VARMA

Garten Stuhl-2
Hi all,



I want to estimate parameters from a VARMA(p,q)-Modell.



The equations of the model or the model structures is given by:



Xt=beta1+beta2*Xt-1+beta3*Yt-1+epsilon1

Yt=beta4+beta5*Yt-1+espilon2



epsilon1 and espilon2 are white noise.



Xt is given by a vector of n elements e.g. (2, 4, 7, 9, …,n)’ and Yt is
given by a vector of n elements e.g. (4,9,12,17,…,n)’.



The lineVar from tsDyn allows estimating VAR(p)-processes but not
VARMA(p,q)-processes and support not the explained model structure of Xt and
Yt.



Is there any easy understandable program available that supports estimation
of these model parameters ?



Thanks so much.



Best,

Thomas

        [[alternative HTML version deleted]]


______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: VARMA

Giovanni Petris

Package dse does.

HTH,
Giovanni

On Wed, 2010-12-08 at 17:45 +0100, Garten Stuhl wrote:

> Hi all,
>
>
>
> I want to estimate parameters from a VARMA(p,q)-Modell.
>
>
>
> The equations of the model or the model structures is given by:
>
>
>
> Xt=beta1+beta2*Xt-1+beta3*Yt-1+epsilon1
>
> Yt=beta4+beta5*Yt-1+espilon2
>
>
>
> epsilon1 and espilon2 are white noise.
>
>
>
> Xt is given by a vector of n elements e.g. (2, 4, 7, 9, ,n) and Yt is
> given by a vector of n elements e.g. (4,9,12,17,,n).
>
>
>
> The lineVar from tsDyn allows estimating VAR(p)-processes but not
> VARMA(p,q)-processes and support not the explained model structure of Xt and
> Yt.
>
>
>
> Is there any easy understandable program available that supports estimation
> of these model parameters ?
>
>
>
> Thanks so much.
>
>
>
> Best,
>
> Thomas
>
> [[alternative HTML version deleted]]
>
> ______________________________________________
> [hidden email] mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: VARMA

Garten Stuhl-2
I used estVARXls from dse, but it doesn’t run. Can anybody give me a simple
example?



model <- estVARXls(c)



R gives me: Fehler in x$input : $ operator is invalid for atomic vectors



c is a matrix with 2 columns with measured values.



Whats my mistake?



Best,

Thomas

2010/12/9 Giovanni Petris <[hidden email]>

>
> Package dse does.
>
> HTH,
> Giovanni
>
> On Wed, 2010-12-08 at 17:45 +0100, Garten Stuhl wrote:
> > Hi all,
> >
> >
> >
> > I want to estimate parameters from a VARMA(p,q)-Modell.
> >
> >
> >
> > The equations of the model or the model structures is given by:
> >
> >
> >
> > Xt=beta1+beta2*Xt-1+beta3*Yt-1+epsilon1
> >
> > Yt=beta4+beta5*Yt-1+espilon2
> >
> >
> >
> > epsilon1 and espilon2 are white noise.
> >
> >
> >
> > Xt is given by a vector of n elements e.g. (2, 4, 7, 9, ,n) and Yt is
> > given by a vector of n elements e.g. (4,9,12,17,,n).
> >
> >
> >
> > The lineVar from tsDyn allows estimating VAR(p)-processes but not
> > VARMA(p,q)-processes and support not the explained model structure of Xt
> and
> > Yt.
> >
> >
> >
> > Is there any easy understandable program available that supports
> estimation
> > of these model parameters ?
> >
> >
> >
> > Thanks so much.
> >
> >
> >
> > Best,
> >
> > Thomas
> >
> >       [[alternative HTML version deleted]]
> >
> > ______________________________________________
> > [hidden email] mailing list
> > https://stat.ethz.ch/mailman/listinfo/r-help
> > PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html<http://www.r-project.org/posting-guide.html>
> > and provide commented, minimal, self-contained, reproducible code.
>
>
>
        [[alternative HTML version deleted]]


______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.