Hello, I need something like
 
y_t = (B(L)/A(L)) x_t + (C(L)/A'(L)) u_t
 
where L is the lag operator and u_t is a white noise sequence and A(L) and A'(L) are different. I think  --conditional option doesn't do that and in the manual I haven't found it. Is it possible?
 
Thank you very much.
Nieves.


> Date: Tue, 12 Feb 2008 22:13:35 +0100
> From: r.lucchetti@univpm.it
> To: gretl-users@lists.wfu.edu
> Subject: Re: [Gretl-users] Tranfer function models
>
> On Tue, 12 Feb 2008, Nieves Sánchez Martínez wrote:
>
> >
> > Hello, I need to use transfer function models but I don't know if Gretl
> > can do it. I've read Gretl help documents and I haven't found it. Could
> > you please tell me how can I do it using Gretl (if possible)?
>
> If what you need is a univariate model of the kind
>
> A(L)y_t = B(L)x_t + C(L)u_t
>
> where L is the lag operator and u_t is a white noise sequence, that's
> exactly what the "arima" command, with the --conditional option, does. In
> the graphical client, you must select Model>Time series>ARIMA and select
> "Conditional maximum likelihood" just above the "Help" button (by default,
> exact maximum likelihood is used, which estimates something different).
>
> You'll find a more complete discussion in the manual.
>
>
> Riccardo (Jack) Lucchetti
> Dipartimento di Economia
> Universitŕ Politecnica delle Marche
>
> r.lucchetti@univpm.it
> http://www.econ.univpm.it/lucchetti

---

Sigue al minuto las principales noticias de tu ciudad MSN Deportes