I think Aymen means to have the same lags in each equation, but with a
"gappy" structure, for example include the first and third lags, but not
the second (everywhere). Then the VAR-OLS-estimation would still apply.

Vaguely I think there was a discussion about this some time back, but I
don't remember the result. Of course it's still possible to specifiy
this manually as a system and do OLS, but it's not very convenient.

sorry,
sven


Am 28.04.2013 20:54, schrieb Summers, Peter:
> Aymen,
>
> If your lags differ in each equation, it's not really a VAR. However
> you could specify the equations separately and estimate them as a SUR
> model. Have a look at the "system" command.
>
> I hope this helps,
>
> PS ________________________________________ From:
> gretl-users-bounces@lists.wfu.edu [gretl-users-bounces@lists.wfu.edu]
> on behalf of aymen kaabi [kaabiayman@gmail.com] Sent: Sunday, April
> 28, 2013 12:34 PM To: Gretl list Subject: [Gretl-users] vector
> autoregressive
>
> good  evening
>
>
> i have a problem with gretl_var.
>
> first with the function ar_model i can specify the lags
>
> FOR EXAMPLE: Yt= Yt-3 + Y t-2 + Yt-6 +CONST    but with gretl I CAN'T
> i just enter the lag order .
>
> HOW can i specify the lags .
>
> my project work personalized lags please answer me .
>
>
> thanks for all
>
> _______________________________________________ Gretl-users mailing
> list Gretl-users@lists.wfu.edu
> http://lists.wfu.edu/mailman/listinfo/gretl-users
>

_______________________________________________
Gretl-users mailing list
Gretl-users@lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users