Re: [Gretl-users] Gretl-users Digest, Vol 92, Issue 9
by Michael Boldin
I doubt that you can restrict the two equations to have the same
variance. They will simply be based on the fit of the estimated a1 and
a2 coefficients. The reason is that VAR coefficients do not depend on
the system's var-cov matrix when maximizing the likelihood function
(unless for some reason the restrictions create a dependence -- but I
fairly sure they do not). This is generally the consequence of having
the same right hand side variables in each equation.
In the end, your 'restrict model1' method is probably the easiest
way to accomplish what you really want.
Alternatively, you could estimate one equation where you stack the
observations so the y1 observations have y1(-1) in the first column
and the y2 observations have y2(-1) in the same column. Then reverse
the case for the second column such that y2(-1) is stacked above
y1(-1).
It is not clear whether you are using restricted or unrestricted
constant terms, but stacked vectors of ones and zeros will accomplish
whatever you desire.
Then the 'one' equation will have a single estimated standard error,
but it will not be 'restricted' in any way.
> From: Dominik Menno <menno(a)vwl.uni-mannheim.de>
> Subject: [Gretl-users] estimate restricted VAR
>
> I would like to estimate a symmetric VAR(1) process
>
> y = A y(-1) + u
>
> where u is random variable with variance covariance matrix S.
>
> Symmetric in the sense that the diagonal elements of A are equal and the
> off-diagonals are equal, i.e. a11 = a22 and a12=a21. But now the
> problem: I also want to restrict the variance covariance matrix to be
> symmetric, that is, the variances should be the same.
>
> Therefore my question: How can I impose restrictions on the estimated
> variance covariance matrix? Any ideas?
10 years
estimate restricted VAR
by Dominik Menno
Dear All,
I would like to estimate a symmetric VAR(1) process
y = Ay(-1) + u
where u is random variable with variance covariance matrix S.
Symmetric in the sense that the diagonal elements of A are equal and the
off-diagonals are equal, i.e. a11 = a22 and a12=a21. But now the
problem: I also want to restrict the variance covariance matrix to be
symmetric, that is, the variances should be the same.
Therefore my question: How can I impose restrictions on the estimated
variance covariance matrix? Any ideas?
What I did:
# set the model up as a system
"model1" <- system
equation y1 const y1(-1) y2(-1)
equation y2 const y2(-1) y1(-1)
endog y1 y2
end system
# and estimate it in various ways
restrict model2
b[1,2]-b[2,2]=0
b[1,3]-b[2,3]=0
end restrict
estimate "model1" method=ols
Thanks a lot and best,
Dominik
--
Dominik Menno
RWTH Aachen University
Templergraben 64
52064 Aachen
Tel: +49 (0)241/80 96 286
Fax: +49 (0)241/80 92 337
dominik.menno(a)rwth-aachen.de
10 years
Fellowship
by Riccardo (Jack) Lucchetti
Ok, folks, here it is.
http://bandi.miur.it/bandi.php/public/fellowship/id_fellow/86791
Now, before you say it: I do realise that if you clock on the link that
you'll find on the page linked above, you'll be transported into an
Italian-only, English-averse world, but this is the way the university I
work for operates :(
Of course, if anybody needs assistance with the language of Dante and
countless operatic masterpieces, I'm ready to offer my help.
-------------------------------------------------------
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
non-linear wald test
by Artur T.
Dear gretl users,
I want to run a Wald test on long-run parameter symmetry based on an
ARDL model. For this I can apply gretl's internal function which is
documented in the help file. However, to be a bit more flexible I
programmed a function which does exactly what is expected, yielding the
same results as gretl's internal procedure. But this does,
unfortunately, hold not in every case.
In the attached script I test the three following hypotheses separately:
1. b[Pinc]/[rho]-b[Ninc]/[rho]=0
2. b[Prt]/[rho]-b[Nrt]/[rho]=0
3. b[Pown]/[rho]-b[Nown]/[rho]=0
For the first two I obtain exactly the same results using either gretl's
internal function or mine. However, for the third one I obtain an error
as the standard errors of the non-linear long-run coefficients
lrse = sqrt(qform(fb,vcv))
cannot be computed. I don't find the issue. Maybe someone has a solution
to this.
Much appreciated.
Artur
10 years
Compiling Gretl on RHEL 5
by Charles Gagnon
I support gretl for a group who uses it, so I don't use it myself. But I'm
running into issues compiling and installing.
I'm trying to deploy the latest gretl-1.9.91 on a RHEL 5.9 box.
The configure script complains that:
Please install glib-2.0 >= 2.12.0 and then reconfigure gretl.
glib-2.0 is available from http://www.gtk.org/
Yet I have glib 2.12.3 installed. I checked in the config.log and it seems
like to be looking for > 2.14 so I'm confused:
configure:17635: $PKG_CONFIG --exists --print-errors "glib-2.0 >= 2.14.0"
Requested 'glib-2.0 >= 2.14.0' but version of GLib is 2.12.3
configure:17652: $PKG_CONFIG --exists --print-errors "glib-2.0 >= 2.14.0"
Requested 'glib-2.0 >= 2.14.0' but version of GLib is 2.12.3
Requested 'glib-2.0 >= 2.14.0' but version of GLib is 2.12.3
I would just upgrade glib but it seems involved since the repository does
not have it available for RHEL 5.
Regards,
--
Charles Gagnon
charlesg at unixrealm.com
10 years
Post-doc position available in Ancona
by Riccardo (Jack) Lucchetti
Attention gretlers:
A post-doc position will be available soon here in Ancona: the idea is to
work together with me and Allin on a brand new, completely redesigned
hansl interpreter.
Candidates should be very good coders, ideally with a good background in
compiler design, gramars, BNF and all that, but budding econometricians
with strong computational skills may also be perfectly suitable for the
job.
I'll post a link to the actual application webpage as soon as it's
available. In the meantime, think about it and spread the word among your
CompSci friends!
-------------------------------------------------------
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
problems with daily data
by Sven Schreiber
Hi,
I have a csv file with daily data, where each calendar day is a row, but
it's actually 5-days-a-week data, i.e. weekend days do not contain data.
First I have a problem with the import, gretl only imports it as undated
because it says about the date labels:
"
erster Zeilenkopf "99-01-04", letzter Kopf "2014-05-19"
Behandlung als undatierte Daten
"
(=treating it as undated), but the reason given is not true, because the
first date string is actually:
"1999-01-04"
so there seems to be some problem with the date parsing.
Ok, I can work around that, defining it manually as 7-days-daily data
with the right starting date. Then I have the interface issue that at
the bottom it only says "daily" (in German), but I think it is important
here to show the distinction between 5- or 6- or 7-days-daily.
Next I would like to convert the workfile from 7-days-daily to
5-days-daily, i.e. remove the empty (=missings) weekends obs, but this
doesn't seem to be easy to do. (Note that removing all missing obs is
not equivalent, because that also eliminates other holidays, which is
another topic. Also I know I could use 'join' together with the source
csv file to do that, but I think it should be easier than that, no?)
When I try to work around that by removing all missing obs (including
the holidays) within the 7-days-daily workfile, I run into the old
problem that gretl then starts treating it as undated and the date
information is lost. Note that I cannot then manually set it to
5-days-daily because of the missing holidays which gretl doesn't know
about, i.e. the imposed dating produces errors, and this accumulates
over time.
The first thing mentioned is a bug, but any ideas about the other stuff?
Thanks,
sven
10 years, 1 month
Absence the Import option from the File>open data menu
by Carlos Andrade
In Gretl 1.9.15cvs, Portuguese version, does not appear the import option
from the File> Open Data menu . How to solve this absence?
--
Atenciosamente,
Prof. Carlos A. S. de Andrade
LAPEA - Laboratório de Pesquisa em Economia Aplicada e Engenharia de
Produção
Universidade Federal de Campina Grande.
Centro de Humanidades
Unidade Acadêmica de Economia
10 years, 1 month
