Changeing ID number in script
by Marcin Błażejowski
Hi,
is it possible to change the ID number of given variable via script?
Marcin
--
Marcin Błażejowski
5 years, 1 month
Re: Function package fcModels
by George Matysiak
Yi-Nung,
Thank you for the prompt fix - all good now.
As an aside, how are you estimating the initial values in the HoltDES
routine- a regression based on a sample of values? Thanks.
Best,
George
*Contact number +48 781 415 432"In God we trust, all others bring data."*
5 years, 1 month
Re: Function package fcModels
by George Matysiak
Allin,
Apologies, but I'm not entirely clear how to access the gretl git and fix -
where can I find the instructions? Thanks.
George
*Contact number +48 781 415 432"In God we trust, all others bring data."*
5 years, 1 month
Re: Function package fcModels (Sven Schreiber)
by George Matysiak
Sven,
Yes, I should have provided more details.
Based on two different data sets, both the AutoSES and HoltDES provide
different RMSE figures from those obtained in R's forecast package. The
fcModel figs are consistently lower, and the differences seem to be roughly
of the order magnitude that the fcModel RMSE squared is approx. equal to
the forecast package RMSE.
5 years, 1 month
Re: Function package fcModels (Sven Schreiber)
by Yi-Nung Yang
George
Thanks for Sven and Allin's responses for me. In particular, Sven gave me a
detailed instruction to revise the fcModel package. I've uploaded a new
version 1.2 to fix the issue you raised for moderation. I think it will be
soon available on the server. Thank you for report the errors.
Yi-Nung
5 years, 1 month
Re: Data labels disappear when choosing Freeze Data Labels
by Allin Cottrell
On Sat, 26 Oct 2019, Peter H. Lemieux wrote:
> Sorry to take so long to respond [...]
And kindly supplied an example where "freezing" the data labels shown
in a gretl plot failed.
I could replicate the problem, and it's now fixed in git and
snapshots. Thanks for the report!
Allin
Previous context:
> On 10/12/19 8:06 AM, Allin Cottrell wrote:
> > On Fri, 11 Oct 2019, Peter H. Lemieux wrote:
> >
> > > Kubuntu 19.10
> > > Gretl 2019c for Linux x86-64
> > > Build date 2019-07-03
> > >
> > > If I swipe across a chart my data labels appear as expected. However when
> > > I choose Freeze Data Labels from the context menu, the labels all
> > > disappear. This is not the behavior I observed in previous versions, nor
> > > obviously the expected behavior.
> >
> > What data file are you working with? If it's not one of those packaged with
> > gretl, could you send me a copy please?
> >
> > I'm not seeing this problem with current git, using the supplied Ramanathan
> > data file data4-10.
5 years, 1 month
Re: Function package fcModels
by George Matysiak
Allin, noted and thanks for the information.
George
*Contact number +48 781 415 432"In God we trust, all others bring data."*
5 years, 1 month
Re: Function package fcModels
by George Matysiak
Great, let's hope there's a fix.
George
*Contact number +48 781 415 432"In God we trust, all others bring data."*
5 years, 1 month
Combined graphics in gretl
by Olasehinde Timmy
Dear Professors,
Please, kindly put me through on how to generate a combined impulse
response graph in SVAR, and also how to include identification matrix in
SVAR estimation via script.
Thanks.
5 years, 1 month
Re: Function package fcModels
by George Matysiak
I have an issue with the RMSE figure in the function* autoSES*. It appears
to be inaccurately calculated. I have crossed-checked against the
equivalent SES RMSE calculation in the *forecast* package in R which does
provide the correct figure. Has anyone had a similar issue? Thanks.
*Contact number +48 781 415 432"In God we trust, all others bring data."*
5 years, 1 month
