removing nan and inf from a matrix
by Logan Kelly
Hello,
I need to take the log difference of a matrix, i.e. log(M[2 rows(M):,]/M[1:rows(M)-1,]). Unfortunately, M has elements equal to zero. I need to replace the nan's and inf's with 0's. This almost works
M = isnan(M) ? 0 : M
but does not remove inf's. Any sugestions?
8 years, 11 months
Feature Request: "--preserve" option
by Henrique Andrade
Dear Gretl Team,
We can use the option "--preserve" with the "open" command to preserve
matrices and scalars. I would like to ask you if it is possible to include
strings too (so the "preserve" option will preserve matrices, scalars, and
strings).
Best regards,
Henrique Andrade
9 years, 11 months
weights in system estimation?
by Simona De Lauretis
Dear Gretl users,
I have a question about system estimation and a (possible) bug report.
The question is: is it possible to include weights for observations when
estimating a system of equations in gretl (with sur method for example)?
I've read in the command reference that the supported estimators
are ols, tsls, sur, 3sls, fiml and liml. However, if I estimate the
system using the
"simultaneous equations" dialog box, there is also wls as one of the
proposed estimators
(but it's not possible to specify a weight variable, so maybe it does
not perform a
weighted regression after all).
The possible bug occurs after the estimation of a system using method
SUR. In the results
window, the command "Tests -> Normality of residuals" is active, but
nothing happens when
I click on it (gretl does not crash either). I'm running gretl 1.10.1
on Windows 7,
but I had the same problem with the previous release.
Thank you and best regards
Simona
10 years
Interrupted time series
by Michael Ott
Does anyone know stepwise how to do an interrupted time series in Gretl. I'm using Gretl on my Mac any help as far as identifying a difference in trend and level would be appreciated
Thanks
Sent from my iPhone
10 years
filledcurve with the new plot environment
by Logan Kelly
Hello,
Is it possible to fill between two line plots using the new plot environment? I would like to reproduce something like the IRF confidence bands produced via the SVAR package. This can be done by writing a gnuplot script file, but I wondered if the new plot environment would be a better way?
Cheers,
Logan
10 years
Gretl working paper series
by Riccardo (Jack) Lucchetti
* WITH THE OBVIOUS APOLOGIES FOR CROSS-POSTING *
After having talked about this for a while in several occasions, finally
we inaugurated the Gretl Working Paper Series, which is hosted at the
Dipartimento di Scienze Economiche e Sociali here in Ancona (thanks for
that) and given proper circulation through the RePEc circuit (IDEAS,
EconPapers, etcetera).
Gretl WP #1, by Claudia Pigini and myself, can be found here:
https://ideas.repec.org/p/anc/wgretl/1.html
Of course, we welcome submissions by anybody. So, I think a few words of
what we have in mind will be useful: the gretl working paper series is
part of the overall gretl project.
As such, its aim is to host:
* "geeky" wps: papers devoted to the analysis of computational
techniques which may be used, at least in part, in the gretl code
for accuracy and/or performance (possible examples: what MPI is and
how to use it in hansl, quadrature techniques, optimisation
methods);
* "development" wps: papers which explore recent developments in
econometrics and implement them in gretl, or at least discuss
possible ways to do so (example: documentation to a particularly
complex function package);
* "practitioners" wps: survey/tutorial papers on some reasonably
advanced and general topic, which discuss how certain techniques can
be implemented in gretl (example: how to do policy evaluation in
Gretl: ATE, ATET, PS matching, RDD and all that; or state-of-the-art
trend-cycle decomposition; or the bootstrap; and so on);
* "empirical" wps: research papers in which you use gretl for some
non-trivial empirical modelling (no OLS, please); or possibly, hefty
Monte Carlo experiments.
* "teacher's corner" wps: comprehensive analysis of certain topics
with a view to their adoption as medium-to-advanced teaching
material in courses which use gretl as the reference software
package (example: something like Lee Adkins' book --- perhaps more
limited in scope: ARMAs, unit roots, panel estimators; but again:
please, no OLS).
If you're interested, please submit your working papers to me
(r.lucchetti(a)univpm.it); at least for the moment, we won't have a
formal peer-review procedure, but we may introduce one in the future
if necessary.
I have a LaTeX style file I can send to you for preparing the final
version after acceptance.
-------------------------------------------------------
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
-------------------------------------------------------
10 years
Gretl conference Berlin 2015 reminder
by Sven Schreiber
Dear Gretl list,
as the local organizer let me remind you of the upcoming biannual
conference, http://www.gretlconference.org/.
You can no longer submit papers for presentation, but you can still
register as a non-presenting participant. Simply email us at
GC2015(a)gretlconference.org or me personally.
Also there are pre-booked hotel rooms available, but this pre-booking
arrangement with the hotel rooms expires in two days (which is actually
the reason why I'm sending this message today). Contact me by email if
you're interested and I will send you the booking forms directly.
Let me add that if you're still not sure whether to come to the
conference, the hotels have a cancellation policy. So you could pre-book
a room and then, if you decide later that you cannot attend, you should
be able to cancel the room at no cost (under certain conditions, please
read the booking forms carefully; we are not responsible for your hotel
booking).
A preliminary program of the conference should be available soon.
Thank you, and hope to see you in Berlin in June,
Sven
10 years
ADF test
by Ana Amaro ISG
Good M:)
About this test i think it would add value if we could analyse the residual correlogram. Sometimes it is not clear that the 'automatic' decision is the one we would select.
:)
Ana Amaro
Sent from my iPhone
Apologize for the brevity/grammar/spelling
10 years
Gretl functions: the "dataset" command
by Henrique Andrade
Dear Gretl Team,
I would like to know if there exists a way to use "dataset" command inside
a function. Please take a look at my code:
<hansl>
open australia.gdt
function list anualizar(series x)
dataset compact 1 last
end function
eval anualizar(PAU)
</hansl>
Best,
Henrique Andrade
10 years
gretl no funciona
by Gilberto Matute Antúnez
Estimados señores:
He tratado de trabajar con Gretl en UBUNTU 14.04 y Liux Mint 17.1, pero
en ninguno de los casos funciona. Se abre y recibe los datos pero cuando
trato de realizar un análisis con los modelos o cuando trato de crear un
gráfico el programa se cierra.
Gracias por su ayuda.
10 years
