Re: [Gretl-users] issue defining a panel with sub-sample data
On Tue, 1 Oct 2013, Summers, Peter wrote:
FWIW, my first thought was to agree with Jack (the user). However I
haven't worked much with panel data so I recognize this may not be the
majority view. It certainly seems non-straightforward.
Just for the record: at one time we padded on sub-sampling of a panel
dataset by default but offered an option to suppress this. The switch to
the current status, where you need the --balanced option to get the
padding, occurred in December 2009, in CVS between gretl versions 1.8.6
and 1.8.7.
The change wasn't documented in the change log, but it followed a
discussion on the users list; see the thread titled "sub-sampling panel
data" at
http://lists.wfu.edu/pipermail/gretl-users/2009-December/thread.html
Artur Bala found the old behavior confusing and I announced a change in
CVS in
http://lists.wfu.edu/pipermail/gretl-users/2009-December/004153.html
At the time there were no objections -- which is not to say that we
shouldn't reopen the issue now.
Allin
-----Original Message-----
From: gretl-users-bounces(a)lists.wfu.edu [mailto:gretl-users-bounces@lists.wfu.edu] On
Behalf Of Riccardo (Jack) Lucchetti
Sent: Tuesday, October 01, 2013 3:08 PM
To: Allin Cottrell
Cc: Gretl list
Subject: Re: [Gretl-users] issue defining a panel with sub-sample data
On Tue, 1 Oct 2013, Allin Cottrell wrote:
> On Tue, 1 Oct 2013, Riccardo (Jack) Lucchetti wrote:
>
>>> This whole thing needs some more investigation. I guess for
>>> consistency we should either scrap the --balanced option or
>>> reactivate the balancing mode that's now disabled. Whenever I try to
>>> think this issue through it makes my head hurt, but I'll see what I can
do...
>>
>> Personal opinion: if a panel structure is in force, --balanced should
>> be implicit in smpl. Rationale: a panel dataset is a panel dataset.
>> It simply can't stop being a panel dataset because you are
>> sub-sampling it. If you really want it to be interpreted differently,
>> then you have setobs for that.
>
> I hear you, but not all users have that expectation. At one time what
> the --balanced option does was the default, but I changed that (a long
> time ago
> now) after hearing from some users that they found the effect
> surprising, even disconcerting ("I thought I'd got rid of those rows,
> but there they still are, just with NAs substituted").
Hm. I'd like very much to reconsider that. Opinions?