Gretl-Hansl "IDE" for Sublime editor
by Artur Tarassow
Dear all,
some weeks ago I've started to switch to the sublime editor
(https://www.sublimetext.com/) for writing gretl code.
Even though I like the simplicity of the gretl editor and its features
such as syntax highlighting and auto-itendation, it lacks some features
of modern IDEs such as "goto-anything", "goto-definition", custom
keybindings, fancy themes, git-implementation, snippets etc. which make
life much easier when working on larger projects. Don't get me wrong,
the gretl editor is great but was _never_ supposed to become a proper
software-development IDE but rather has another focus which is totally fine.
So I started to write the "Hansl-Gretl-Language" package for sublime
which includes the following features:
- 3 gretl build-systems (client mode, batch mode, and REPL mode) for
executing hansl code by means of sublime (plots are also working!)
- syntax-highlighting
- completion of gretl commands, accessors and keywords
- some snippet examples for speeding up coding
The project still has the following (known) issues:
- no auto-itendation (still have to figure out how this works)
- issues with some corner-cases which are not syntax-highlighted (regex
can become so hard!)
The package can be downloaded through sublimes package control system,
and can be found here:
https://packagecontrol.io/packages/Hansl-Gretl-Language
If somebody wants to participate on this project, check out the code on
my github repository:
https://github.com/atecon/Hansl-Gretl-Language
For those interesting in the sublime editor, check out "OdatNurd"'s
brilliant tutorials on youtube:
https://www.youtube.com/user/nurdz
Enjoy the package,
Artur
4 months
BACE Estimation difficulties
by Brian Revell
I thought i would try this option estimating a simple model (always the
best way to gain experience and confidence with the routine).
Independent variable, 1 indep variable . No lag on Y. . Zero selected for
out of sample forecast Constant -can be omitted. Best 4 models selected
-again as the default.
This was the output:-
Dependent viariable was removed from the X list.* It is not there -there is
only a single indep variable. *
Error message from BACE_GUI():
Average model size should be greater then 0 and lower than K !!! *Average
model size specified is the default 1*
*Some guidance wlecomed please*
*Brian*
1 year, 3 months
Re: How to apply the HAC option in Gretl?
by Cottrell, Allin
On Mon, Nov 7, 2022 at 12:29 PM Torbjørn Lorentzen
<torbjorn.lorentzen(a)outlook.com> wrote:
>
> I'm a new user of Gretl. I'm using ols in the estimation of a time series model. T want to us ethe HAC-option to correct for autocorrelation and heteroscedasticity. I tried the robust option, but to what I can see it only corrects for heteroscedasticity? Great if anyone could help me with the Gretl script for HAC and how to put it together with the ols command. All suggestions are appreciated 😊
Hi Tobben. If you go to the menu item /Tools/Preferences/General
you'll see an "HCCME" tab. That lets you set your preferences for
robust covariance matrix estimation. Note that the HAC option is only
available when your dataset is recognized as time-series.
In scripting usage the relevant option is --robust. What exactly that
does depends on the aforementioned setting. But if the data are time
series gretl will use the HAC estimator by default. In that case you
should see a line like the following in the estimation output:
HAC standard errors, bandwidth 4 (Bartlett kernel)
Allin Cottrell
1 year, 3 months
Fwd: possible bug when running midasreg command
by Cottrell, Allin
HI all,
I run the midasreg command . It appears that in some cases does not work at all.
Precisely,after merging the two datasets ( quarterly and monthly data
named consumption_indicator_m.gdt and con_final_q.gdt respectively ,
I create midas lists whose names are
INDICATOR1, INDICATOR2,.... up to INDICATOR12.
It appears that the midasreg command does not work for cases
INDICATOR4, INDICATOR5 and INDICATOR8.
I enclose the two previously mentioned datasets as well as the script
named consumption_midas.inp .
Thanks in advance for your reply,
Dionysio Lalountas
1 year, 4 months
Gretl wiki
by Federico Fiorani
Dear all,
I would like to know your opinion about opening a wiki for Gretl.
I heard that a test had been done but the wiki was closed shortly
afterwards.
In my opinion, a wiki could be very useful, for example, to supplement
what cannot be in the documentation or manual, such as examples of
scripts, or to explore topics that may not be entirely clear at first
glance and It would also be useful for those who are new to the software.
Regards
Federico
1 year, 5 months
Re: Gretl analysis in outliers package
by Riccardo (Jack) Lucchetti
On Thu, 24 Nov 2022, Marco La Cruz wrote:
> Dear All
> I need help in finding a package in Gretl for outliers analysis. Is there
> one in Gretl that does the following as noted in the videos below? If yes
> where can I find it with instructions on how to use it? Can you help me?
>
> *Test for and discuss outliers approach implemented. For outliers analysis
> (see video to detect and correct )** https://youtu.be/NeQep4cwbYI
> <https://youtu.be/NeQep4cwbYI> AND https://youtu.be/aQiZ7uH7JUM
> <https://youtu.be/aQiZ7uH7JUM>*
I believe that at least some of the tools you need can be found, after
estimation, in the Analysis > Influential Observations menu of the model
window.
PS: for future reference, if you want to ask a question like this to the
community, you should use the right email address, that is
gretl-users(a)gretlml.univpm.it
This time, I'm forwarding this to the list, but note that the address you
originally used (gretl-users-owner(a)gretlml.univpm.it) is an administrative
one that we use to manage the list.
-------------------------------------------------------
Riccardo (Jack) Lucchetti
Dipartimento di Scienze Economiche e Sociali (DiSES)
Università Politecnica delle Marche
(formerly known as Università di Ancona)
r.lucchetti(a)univpm.it
http://www2.econ.univpm.it/servizi/hpp/lucchetti
-------------------------------------------------------
1 year, 5 months
The contributed function package "DP" is going to be retired
by Sven Schreiber
Hello everybody,
this is to announce that the contributed function package DP (DP.gfn)
will be removed from the package server in a couple of days.
The reason is that its functionality is already provided natively by
core gretl; the package carries out the Dickey-Pantula test for a double
unit root / I(2)-ness of a time series. In gretl you can perform this
test simply by choosing the option "use first difference of the series"
in the various dialog windows for the different unit root test
incarnations. (Under the "Variable" menu; in script mode use the option
--difference with the adf command -- perhaps we could add to the adf
documentation explicitly the keyword Dickey-Pantula.)
This redundancy was probably not the case when the package was first
published. In any case, the package hasn't been updated since 2015 and
the author Uriel could not be reached anymore. (Uriel, if by any chance
you are reading this: greetings, and it would be great to get your
current email address.)
If --for whichever reason-- you still need to use the package in the
future, you would have to keep a private copy of the gfn package file on
your system.
cheers
sven
1 year, 5 months
Wooldridge data sets in need of some revision?
by Riccardo (Jack) Lucchetti
Hi all,
a user brought to my attention the following slight glitch: assuming you
have the "Wooldridge" dataset collection installed, the following script
<hansl>
open fertil3.gdt
setobs 1 1913
ols gfr time tsq gfr_1
</hansl>
produces an ols printout where gretl displays the DW statistic instead of
Durbin's h, as it should (since the lagged dependent variable is among the
regressors).
This is no gretl bug: it's a consequence of the fact that the
"fertil3.gdt" dataset does not contain the proper calendar information
and, more importantly, the lagged variables are stored in the dataset but
are not marked as such. A slight modification of the above script that
deals with this problem could be
<hansl>
open fertil3.gdt
setobs 1 1913
delete gfr_*
ols gfr const time gfr(-1)
</hansl>
where the lags of "gfr" are cleaned first and then regenerated on the fly
as needed.
Nevertheless, it would be nice if gretl shipped a version of this dataset
in which this issue is fixed. Is there anyone who uses regularly the
Wooldridge example files who could spend an hour compiling a list of the
data files that need fixing?
-------------------------------------------------------
Riccardo (Jack) Lucchetti
Dipartimento di Scienze Economiche e Sociali (DiSES)
Università Politecnica delle Marche
(formerly known as Università di Ancona)
r.lucchetti(a)univpm.it
http://www2.econ.univpm.it/servizi/hpp/lucchetti
-------------------------------------------------------
1 year, 5 months
Re: VAR modeling
by Cottrell, Allin
On Fri, Nov 11, 2022 at 5:28 AM Agustín Alonso Rodríguez
<aalonso(a)rcumariacristina.com> wrote:
>
> How to refine or simplify a VAR model suppressing the insignificant estimated coefs?
You have a reply from Sven, noting that gretl does not currently have
a built-in procedure for what you describe. That's true, but I'll
offer a somewhat different perspective.
When you estimate a VAR with p lags of each variable, you should not
be too concerned with the "statistical significance" of each
coefficient -- and not too quick to eliminate terms that are
"insignificant". If the VAR is in levels, in particular, it's likely
that the several lags of a given variable will be strongly correlated.
This then gives you the classic "multicollinearity" effect, whereby
each individual coefficient may be "insignificant" yet a joint test
strongly rejects the null hypothesis that the "collinear" variables
all have coefficients equal to zero. Gretl shows you the joint (F)
tests after estimating a VAR -- that is, tests for Granger causality
-- and you might be better off using these to eliminate one or more
variables from your specification (if warranted) rather than worrying
about individual lagged terms.
Allin Cottrell
1 year, 5 months
Re: Gretl-users Digest, Vol 190, Issue 18
by Agustín Alonso Rodríguez
Thanks a lot.
Agustin Aloonso-Rodriguez
-----Mensaje original-----
De: gretl-users-request(a)gretlml.univpm.it <gretl-users-request(a)gretlml.univpm.it>
Enviado el: sábado, 12 de noviembre de 2022 0:00
Para: gretl-users(a)gretlml.univpm.it
Asunto: Gretl-users Digest, Vol 190, Issue 18
Send Gretl-users mailing list submissions to
gretl-users(a)gretlml.univpm.it
To subscribe or unsubscribe via email, send a message with subject or body 'help' to
gretl-users-request(a)gretlml.univpm.it
You can reach the person managing the list at
gretl-users-owner(a)gretlml.univpm.it
When replying, please edit your Subject line so it is more specific than "Re: Contents of Gretl-users digest..."
Today's Topics:
1. Re: VAR modeling (Cottrell, Allin)
----------------------------------------------------------------------
Date: Fri, 11 Nov 2022 15:49:50 -0500
From: "Cottrell, Allin" <cottrell(a)wfu.edu>
Subject: [Gretl-users] Re: VAR modeling
To: Gretl list <gretl-users(a)gretlml.univpm.it>
Message-ID:
<CA+BOgOAzH_JAytimC9ENt-s+cRdLY21AKNShdhDARtHAR+ZkNg(a)mail.gmail.com>
Content-Type: text/plain; charset="UTF-8"
On Fri, Nov 11, 2022 at 5:28 AM Agustín Alonso Rodríguez <aalonso(a)rcumariacristina.com> wrote:
>
> How to refine or simplify a VAR model suppressing the insignificant estimated coefs?
You have a reply from Sven, noting that gretl does not currently have a built-in procedure for what you describe. That's true, but I'll offer a somewhat different perspective.
When you estimate a VAR with p lags of each variable, you should not be too concerned with the "statistical significance" of each coefficient -- and not too quick to eliminate terms that are "insignificant". If the VAR is in levels, in particular, it's likely that the several lags of a given variable will be strongly correlated.
This then gives you the classic "multicollinearity" effect, whereby each individual coefficient may be "insignificant" yet a joint test strongly rejects the null hypothesis that the "collinear" variables all have coefficients equal to zero. Gretl shows you the joint (F) tests after estimating a VAR -- that is, tests for Granger causality
-- and you might be better off using these to eliminate one or more variables from your specification (if warranted) rather than worrying about individual lagged terms.
Allin Cottrell
------------------------------
Subject: Digest Footer
_______________________________________________
Gretl-users mailing list -- gretl-users(a)gretlml.univpm.it To unsubscribe send an email to gretl-users-leave(a)gretlml.univpm.it
Website: https://gretlml.univpm.it/postorius/lists/gretl-users.gretlml.univpm.it/
------------------------------
End of Gretl-users Digest, Vol 190, Issue 18
********************************************
1 year, 5 months
