[R]how to estimate adding-regression GARCH Model

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

[R]how to estimate adding-regression GARCH Model

mayuchao
 Hello, R people:

     I have a question in using fSeries package--the funciton garchFit and
garchOxFit
  if adding a regression to the  mean formula, how to estimate the model in
R? using garchFit or garchOxFit?
   For example, Observations is {x,y}_t,there may be some relation between x
and y.
   the model is
    y_t=gamma0 + *gamma1*x_t*+psi*e_{t-1}+e_t       the gamma1*x_t is
regression.
    e_t=sqrt(h_t)*N(0,1)
    h_t=alpha0+alpha1*e_t^2+beta*h_{t_1}~~~~~~~GARCH(1,1).
    I  didn't know how to estimate the model using function garchFit or
garchOxFit or other functions?    because the argument in
garchFit/garchOxFit is formular.mean=~arma(1,1).

   Do you have some instrucitons?
   thank you very much for you help.

Best wishes

Ma Yuchao

        [[alternative HTML version deleted]]

_______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
Reply | Threaded
Open this post in threaded view
|

Re: [R]how to estimate adding-regression GARCH Model

Diethelm Wuertz
The supported models are restircted to those listed in the help page.
For the family of GARCH models these are in its moste general form

    ARMA(m,n)-APARCH(p,q).

I have not considered to add regression.

Diethelm Wuertz


   



ma yuchao wrote:

> Hello, R people:
>
>     I have a question in using fSeries package--the funciton garchFit and
>garchOxFit
>  if adding a regression to the  mean formula, how to estimate the model in
>R? using garchFit or garchOxFit?
>   For example, Observations is {x,y}_t,there may be some relation between x
>and y.
>   the model is
>    y_t=gamma0 + *gamma1*x_t*+psi*e_{t-1}+e_t       the gamma1*x_t is
>regression.
>    e_t=sqrt(h_t)*N(0,1)
>    h_t=alpha0+alpha1*e_t^2+beta*h_{t_1}~~~~~~~GARCH(1,1).
>    I  didn't know how to estimate the model using function garchFit or
>garchOxFit or other functions?    because the argument in
>garchFit/garchOxFit is formular.mean=~arma(1,1).
>
>   Do you have some instrucitons?
>   thank you very much for you help.
>
>Best wishes
>
>Ma Yuchao
>
> [[alternative HTML version deleted]]
>
>_______________________________________________
>[hidden email] mailing list
>https://stat.ethz.ch/mailman/listinfo/r-sig-finance
>
>  
>

_______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
Reply | Threaded
Open this post in threaded view
|

Re: [R]how to estimate adding-regression GARCH Model

mayuchao
---------- Forwarded message ----------
From: ma yuchao <[hidden email]>
Date: 2006-5-22 ÏÂÎç9:54
Subject: Re: [R-sig-Finance] [R]how to estimate adding-regression GARCH
Model
To: Diethelm Wuertz <[hidden email]>

 Thank you very much.

But if I want to add regression, is the estimate procedure  different from
general 6 procedure
which is listed in garch.pdf (Parameter Estimation of ARMA Models with
GARCH/APARCH Errors
An R and SPlus Software Implementation)?

I know that the Ox with G@RCH can do regression in garch model.
I didn't know how to modify the garchOxFit funciton.
I try to use fix(garchOxFit) open the funciton, but I am not sure what these
codes means, so failed.

does anyone know how to fix it?

Thank all of you.

Best Wishes

Ma Yuchao

Academy of Mathematics and System Science
Chinese Academy of Science

2006/5/22, Diethelm Wuertz <[hidden email]>:

> The supported models are restircted to those listed in the help page.
> For the family of GARCH models these are in its moste general form
>
>    ARMA(m,n)-APARCH(p,q).
>
> I have not considered to add regression.
>
> Diethelm Wuertz
>
>
>
>
>
>
> ma yuchao wrote:
>
> > Hello, R people:
> >
> >     I have a question in using fSeries package--the funciton garchFit
> and
> >garchOxFit
> >  if adding a regression to the  mean formula, how to estimate the model
> in
> >R? using garchFit or garchOxFit?
> >   For example, Observations is {x,y}_t,there may be some relation
> between x
> >and y.
> >   the model is
> >    y_t=gamma0 + *gamma1*x_t*+psi*e_{t-1}+e_t       the gamma1*x_t is
> >regression.
> >    e_t=sqrt(h_t)*N(0,1)
> >    h_t=alpha0+alpha1*e_t^2+beta*h_{t_1}~~~~~~~GARCH(1,1).
> >    I  didn't know how to estimate the model using function garchFit or
> >garchOxFit or other functions?    because the argument in
> >garchFit/garchOxFit is formular.mean=~arma(1,1).
> >
> >   Do you have some instrucitons?
> >   thank you very much for you help.
> >
> >Best wishes
> >
> >Ma Yuchao
> >
> >       [[alternative HTML version deleted]]
> >
> >_______________________________________________
> >[hidden email] mailing list
> >https://stat.ethz.ch/mailman/listinfo/r-sig-finance
> >
> >
> >
>
>
        [[alternative HTML version deleted]]


_______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance