12:29 p.m.
Dear devel folks,
I just noticed that three days ago an open feature request on the
tracker had its first birthday! Happy birthday to request 1833159, which
by pure coincidence was posted by myself on November 16th, 2007.
But seriously, the request is about "add[ing the] ability to modify an
existing model". The idea was to be able to re-open a saved model and
for example add another lag or perform other modifications, as in other
programs. Essentially this would mean to have a button or menu entry in
the model window, which would open the relevant model specification
dialog with the input fields already filled in with the values of the
saved model.
I think one year is enough time to think about the issue in the sense
that if the actual workers/coders don't like it then we could close the
request as "wontfix" or something like that, or else set some sort of
target, as in which upcoming version the feature would start to appear.
thanks,
sven
12:34 p.m.
Am 19.11.2008 13:29, Sven Schreiber schrieb:
Dear devel folks,
I just noticed that three days ago an open feature request on the
tracker had its first birthday! Happy birthday to request 1833159, which
by pure coincidence was posted by myself on November 16th, 2007.
But seriously, the request is about "add[ing the] ability to modify an
existing model". The idea was to be able to re-open a saved model and
for example add another lag or perform other modifications, as in other
programs. Essentially this would mean to have a button or menu entry in
the model window, which would open the relevant model specification
dialog with the input fields already filled in with the values of the
saved model.
I think one year is enough time to think about the issue in the sense
that if the actual workers/coders don't like it then we could close the
request as "wontfix" or something like that, or else set some sort of
target, as in which upcoming version the feature would start to appear.
-ping-
wontfix or target version 1.8/2.0?
thanks,
sven
8:42 p.m.
On Thu, 4 Dec 2008, Sven Schreiber wrote:
Am 19.11.2008 13:29, Sven Schreiber schrieb:
> I just noticed that three days ago an open feature request on the
> tracker had its first birthday! Happy birthday to request 1833159, which
> by pure coincidence was posted by myself on November 16th, 2007.
>
> But seriously, the request is about "add[ing the] ability to
> modify an existing model". The idea was to be able to re-open
> a saved model and for example add another lag or perform other
> modifications, as in other programs. Essentially this would
> mean to have a button or menu entry in the model window, which
> would open the relevant model specification dialog with the
> input fields already filled in with the values of the saved
> model.
wontfix or target version 1.8/2.0?
Sorry for the delay. I can't promise it'll happen quickly, but
it's doable if a little complicated. How about, perhaps, an entry
in the Analysis menu of the model window, something like "Related
model...".
Allin.
2:21 p.m.
Allin Cottrell schrieb:
On Thu, 4 Dec 2008, Sven Schreiber wrote:
> Am 19.11.2008 13:29, Sven Schreiber schrieb:
>> I just noticed that three days ago an open feature request on the
>> tracker had its first birthday! Happy birthday to request 1833159, which
>> by pure coincidence was posted by myself on November 16th, 2007.
>>
>> But seriously, the request is about "add[ing the] ability to
>> modify an existing model". The idea was to be able to re-open
>> a saved model and for example add another lag or perform other
>> modifications, as in other programs. Essentially this would
>> mean to have a button or menu entry in the model window, which
>> would open the relevant model specification dialog with the
>> input fields already filled in with the values of the saved
>> model.
> wontfix or target version 1.8/2.0?
Sorry for the delay. I can't promise it'll happen quickly, but
it's doable if a little complicated. How about, perhaps, an entry
in the Analysis menu of the model window, something like "Related
model...".
IMHO the Edit menu (second from the left) would be more intuitive; it's
also quite under-used so far with only one entry. But in general a menu
item is perfectly fine for this functionality. In terms of the wording
what about putting the words 'modify' or 'spin off' in there somehow?
(But I gladly let the native speakers make that decision.)
And another thing, maybe warranting another thread if people have strong
opinions about this: After compiling a fresh cvs checkout today I
noticed the 'compute DW p-value' checkbox in the OLS dialog. Personally
I really think that the value added of a DW test with p-values is very
small given the alternative LM tests. Jack has also commented on this.
So I think that even just mentioning the DW test in such a basic and
general dialog is not a good idea. In fact and without wanting to offend
anyone I think it's a very bad idea. (unless I am missing something,
same caveat as always) So I would like to see it go away before the next
release; if people need the functionality, I would propose to add the
possibility to access the DW p-value from somewhere in the model window
after it is estimated, not at the stage of specifying the model.
thanks,
sven
2:37 p.m.
On Fri, 5 Dec 2008, Sven Schreiber wrote:
And another thing, maybe warranting another thread if people
have strong opinions about this: After compiling a fresh cvs
checkout today I noticed the 'compute DW p-value' checkbox in
the OLS dialog... [and didn't like it]
I take your point about this. I think what I'm inclined to do for
the next release is remove that check box, and also remove the
(not yet documented) --dw-pval estimation option, but make the
information available in this way: (a) via the GUI, with an item
on the Tests menu, and (b) via script, with a post-estimation
accessor, $dwpval.
Allin.
9:12 p.m.
Am 05.12.2008 15:37, Allin Cottrell schrieb:
On Fri, 5 Dec 2008, Sven Schreiber wrote:
> And another thing, maybe warranting another thread if people
> have strong opinions about this: After compiling a fresh cvs
> checkout today I noticed the 'compute DW p-value' checkbox in
> the OLS dialog... [and didn't like it]
I take your point about this. I think what I'm inclined to do for
the next release is remove that check box, and also remove the
(not yet documented) --dw-pval estimation option, but make the
information available in this way: (a) via the GUI, with an item
on the Tests menu, and (b) via script, with a post-estimation
accessor, $dwpval.
Thanks, I really appreciate it, and the solution sounds good. I hope I
didn't sound overly harsh, otherwise I apologize.
cheers,
sven
5912
days inactive
5928
days old
5 comments
2 participants
participants (2)
-
Allin Cottrell -
Sven Schreiber