Re: [EXTERNAL] Re: bug in test stat calculator
by Sven Schreiber
Am 03.09.2024 um 17:54 schrieb Summers, Peter:
>
> Ok, I’ve sorted it out. It’s not a bug after all, but there is a typo
> in the documentation. Everything works if the restriction is (female =
> 0), but not with (female == 0). The documentation specifies “==” in
> the “var2 op val” line & below.
>
I see what you mean and I actually do think it's a bug. Years ago gretl
switched from "=" to "==" as the required (or sometimes only preferred)
equality testing operator, and this case apparently was overlooked or
got broken afterwards.
>
> I didn’t know this feature existed before today – I think my students
> will really like it!
>
Yeah, it's a hidden gem... (even if documented)
-s
2 years, 1 month
Re: [EXTERNAL] Re: bug in test stat calculator
by Sven Schreiber
Am 03.09.2024 um 17:36 schrieb Summers, Peter:
>
> Hi Sven,
>
> Yes, I typed the restrictions in parentheses and hit the enter key as
> described. Is the latest snapshot more recent than 08-05?
>
Actually I don't expect that the vintage of the snapshot makes a
difference in this case (although you never know...).
Could you try with a public/example dataset that comes with gretl and be
very precise which restrictions you are trying? Perhaps even a small
screenshot. Maybe you're trying something that leaves one subsample
empty, or similar.
cheers
sven
2 years, 1 month
Re: bug in test stat calculator
by Sven Schreiber
Am 03.09.2024 um 16:56 schrieb Summers, Peter:
>
> Hi all,
>
> I’m trying to follow the sub-sample restriction example in the help
> menu for the test statistic calculator for comparing 2 means. I select
> the same variable in both slots and specify the restrictions, but when
> I hit the enter key the mean, std. dev. & sample size boxes get
> cleared out. Am I missing something? This is on Widows, gretl 2024c-git.
>
Hi Peter, it works for me here with the latest snapshot, actually it's
the first time I have done this. Did you put the restriction in
parentheses as described? Did you hit enter while the variable selection
box had the focus? I think this is also necessary.
So thanks for the reminder about the help text there - I would never
have guessed from the interface that something like that was possible.
I'm wondering whether perhaps the restriction formulation should get its
own optional field to make it clearer.
cheers
sven
2 years, 1 month
bug in test stat calculator
by Summers, Peter
Hi all,
I'm trying to follow the sub-sample restriction example in the help menu for the test statistic calculator for comparing 2 means. I select the same variable in both slots and specify the restrictions, but when I hit the enter key the mean, std. dev. & sample size boxes get cleared out. Am I missing something? This is on Widows, gretl 2024c-git.
Thanks,
Peter
Dr. Peter M. Summers| Associate Professor of Economics
Faculty Advisor, HPU Chess Club
One University Parkway, High Point, NC 27268
Office: 336-841-9650
Choose to be extraordinary!(r)
[Facebook logo]<https://www.facebook.com/HighPointU>[Twitter logo]<https://twitter.com/HighPointU>[Instagram logo]<http://instagram.com/highpointu>[LinkedIn logo]<https://www.linkedin.com/school/28206>
2 years, 1 month
contrib. package Box_Cox_Value to be retired
by Sven Schreiber
Dear all (again),
this message is indirectly related to yesterday's announcement about an
update of the BoxCoxFuncForm package: the similarly named package
Box_Cox_Value by Pedro Isaac Chávez López, dating back from 2014, is
going to be retired from the official package server in a couple of
weeks. Pedro signalled to us that the package isn't maintained anymore,
and the functionality of estimating an optimal Box-Cox transformation
for a single series is now covered by the newer BoxCoxFuncForm package
as well, after its recent update to v0.5.
(There's one (arguably minor) thing that users would have to do manually
now: For series with negative values, the old Box_Cox_Value package
shifted the series to the right, to the strictly positive region. Users
of the newer BoxCoxFuncForm package would have to apply this shift
themselves in a prior step, if it makes sense to do so.)
If for some reason you depend on Box_Cox_Value, please save a local copy
of the package for your own future use.
As always, if you have questions on the usage of the newer package,
you're welcome to ask them here.
cheers
sven
2 years, 1 month
