Gretl request
by Daniel Arribas
Hi there!
I have a problem when I try to install gretl on Ubuntu 7.10. I´ve tried both
the binaries and from source. Apparently I do success with the binaries
since gretl´s icon shows up on Applications, but when i click on it, nothing
happens. Trying to install it from source code stops when it asks me to
install a package I already have installed from synaptic. Any suggestions on
how to have it running on Ubuntu 7.10? Thanks a lot.
One more question: is there any way to generate a new variable which is the
rank of an already existing one (so that biggest value on the existing
variable gets 1, second biggest 2, and so on...).
Thanks a lot from Spain,
d/
--
Daniel Arribas
Department of Economic Analysis
Faculty of Business and Economics
University of Zaragoza (www.unizar.es)
Gran Vía, 2
50005 Zaragoza
SPAIN
16 years, 2 months
eigen values
by Talha Yalta
While preparing the notes for my econometrics class, I noticed that
for Table_10.5.gdt from the Gujarati dataset, Gujarati reports that
the Condition Index is found by SAS as \sqrt{3.0/0.00002422} (the
squareroot of the biggest eigenvalue divided by the smallest)
When I choose from the menu: View--Principal components, I see the
eigen values reported as 2.9720 and 0.0009 (instead of 0.00002422)
Can this be due to an accuracy error?
Regards
Talha
--
"Remember not only to say the right thing in the right place, but far
more difficult still, to leave unsaid the wrong thing at the tempting
moment." - Benjamin Franklin (1706-1790)
--
16 years, 2 months
Single ARIMA Command with Seasonal Differences
by Tom La Bone
Greetings,
I have some quarterly data U1 (variable 1) I would like to model the data as
an ARIMA process. I take the first difference of U1 to create d_U1 (variable
3) and then take the first difference of d_U1 to create d_d_U1 (variable 4).
Finally, I take the seasonal difference to create sd_d_d_U1 (variable 5) and
try an ARIMA(0,0,1) model. The Gretl commands are:
diff U1
diff d_U1
sdiff d_d_U1
arima 0 0 1 ; 5
I would like to do all of this in one command. I have tried a number of
different commands looking something like
arima 0 2 1 ; 0 1 0 ; 1
but have been unable to get the same answers as I did doing the evaluation
step-by-step. Can someone suggest how I can go about doing this with one
command?
Tom
16 years, 2 months
Reading very large data files on Windows
by Allin Cottrell
This is a follow-up to Franck's observation of apparent corruption
in reading a very large (I'm not quite sure how big) data file in
gzipped XML (.gdt) format.
Franck did what I suggested (unzipped the file and looked at the
XML) and found it was fine inside. The problem was in the
unzipping performed by gretl. I've updated the version of
zlib1.dll included in the gretl installer
http://ricardo.ecn.wfu.edu/pub/gretl/gretl_install.exe
and Franck tells me it works OK now.
--
Allin Cottrell
Department of Economics
Wake Forest University, NC
16 years, 2 months
RE: [Gretl-users] Tranfer function models
by Riccardo (Jack) Lucchetti
On Wed, 13 Feb 2008, Nieves Sánchez Martínez wrote:
>
> Hello,
> I need something like
>
> y_t = (B(L)/A(L)) x_t + (C(L)/A'(L)) u_t
>
> where L is the lag operator and u_t is a white noise sequence and A(L)
> and A'(L) are different. I think --conditional option doesn't do that
> and in the manual I haven't found it. Is it possible?
Short answer: yes and no :-)
Long answer: what arma --conditional can handle is the special case
A(L) = A'(L). What you can do is write a script that estimates the general
case, perhaps via MLE, or via the multi-stage approach described in
Brockwell & Davis. All the tools you need are in gretl already, but you
don't get a pre-cooked estimator, you have to write it yourself. One of
the things we are considering for the next release, or possible the one
after, is a user-level implementation of the Kalman filter, which should
make this task (relatively) painless.
Riccardo (Jack) Lucchetti
Dipartimento di Economia
Università Politecnica delle Marche
r.lucchetti(a)univpm.it
http://www.econ.univpm.it/lucchetti
16 years, 2 months
Tranfer function models
by Nieves Sánchez Martínez
Hello,
I need to use transfer function models but I don't know if Gretl can do it. I've read Gretl help documents and I haven't found it. Could you please tell me how can I do it using Gretl (if possible)?
Thank you very much.
Nieves Sánchez.
_________________________________________________________________
Tecnología, moda, motor, viajes,…suscríbete a nuestros boletines para estar siempre a la última
http://newsletters.msn.com/hm/maintenanceeses.asp?L=ES&C=ES&P=WCMaintenan...
16 years, 2 months
problem with simulation loop times
by Sven Schreiber
Hi gretl-listers,
I have a problem with running times of a simulation of mine. IMO the
time needed should grow linearly with the number of simulation runs, but
it turns out that instead it is the "marginal cost" of an extra 100 runs
which grows linearly; each additional 100 runs seem to take about 4 or 5
seconds more than the previously added 100 runs (see below for the numbers).
This essentially simulates data and estimates Vecms. For 200 runs, data
simulation takes about 1/3 of the total time (5s), the estimation close
to the rest (9s, 1s is remaining overhead). The sorting of the results
with gretl's quantile() function is not significantly costly. I don't
think that RAM limitations are a problem, it's not that much data
actually, it's just CPU intensive.
One guess is that the huge script text output may be responsible for
part of the problem -- here it would help if a VECM could be estimated
without any output, as I was suggesting in a previous email (vecm with
the --silent option).
But that is just one guess, and I don't really know what's happening.
Any hints or remarks? I'm not posting the code because it's quite complex.
thanks,
sven
100: Elapsed time: 5.530000
(Diff: 10)
200: Elapsed time: 15.090000
(Diff: 14)
300: Elapsed time: 29.180000
(Diff: 19)
400: Elapsed time: 47.700000
(Diff: 23)
500: Elapsed time: 70.750000
(Diff: 27)
600: Elapsed time: 98.170000
(Diff: 32)
700: Elapsed time: 130.090000
(Diff: 39 -- gretl not always the only active task)
800: Elapsed time: 168.830000 (35810 lines in script output, 1.6MB)
(Diff: 41)
900: Elapsed time: 209.550000
(Diff: 47)
1000: Elapsed time: 257.090000 (51110 lines in script output, 2.3MB)
20000: ran overnight, no result, gretl still at 100% CPU, killed it.
16 years, 2 months
Re: Gretl-users Digest, Vol 13, Issue 3
by Mixon, Wilson
Re: Gretl texbook
Tom asks:
In my question about documentation I guess I am asking if there is a
textbook that explains times series analysis as it is implemented in Gretl,
i.e., is there a times series textbook where the author planned on the
students using Gretl (like ITSM is used in Brockwell and Davis).
One might consider
Using gretl for Principles of Econometrics, 3rd edition This book is a manual for using gretl suitable for use in an introductory econometrics class. It has been written specifically for Hill, Griffiths, and Lim's Principles of Econometrics, 3rd edition, published by John Wiley and Sons, 2008. In the book, I show you how to use gretl to work all of the examples in POE. The data for the examples is packaged for installation into gretl and can be found by following the links below.
(Description from the web site: http://www.learneconometrics.com/gretl.html
-----Original Message-----
From: gretl-users-bounces(a)lists.wfu.edu on behalf of gretl-users-request(a)lists.wfu.edu
Sent: Mon 2/4/2008 3:40 AM
To: gretl-users(a)lists.wfu.edu
Subject: Gretl-users Digest, Vol 13, Issue 3
Send Gretl-users mailing list submissions to
gretl-users(a)lists.wfu.edu
To subscribe or unsubscribe via the World Wide Web, visit
http://lists.wfu.edu/mailman/listinfo/gretl-users
or, via email, send a message with subject or body 'help' to
gretl-users-request(a)lists.wfu.edu
You can reach the person managing the list at
gretl-users-owner(a)lists.wfu.edu
When replying, please edit your Subject line so it is more specific
than "Re: Contents of Gretl-users digest..."
Today's Topics:
1. Tests for Residuals (Tom La Bone)
2. Re: Tests for Residuals (Sven Schreiber)
3. Re: Re: Unit Root Test (Allin Cottrell)
4. RE: Tests for Residuals (Tom La Bone)
5. RE: Tests for Residuals (Allin Cottrell)
6. new string handling (was Re: Unit Root Test) (Allin Cottrell)
7. RE: Tests for Residuals (Allin Cottrell)
8. Re: Tests for Residuals (Sven Schreiber)
----------------------------------------------------------------------
Message: 1
Date: Sun, 3 Feb 2008 10:30:22 -0500
From: "Tom La Bone" <labone(a)gforcecable.com>
Subject: [Gretl-users] Tests for Residuals
To: <gretl-users(a)lists.wfu.edu>
Message-ID: <000301c86679$b2445dc0$6401a8c0@Boozoo>
Content-Type: text/plain; charset="us-ascii"
Good morning,
1) Does Gretl have tests for randomness of residuals accessible as options
from the GUI?
2) From the command line?
3) What references are recommended for folks who interested in the
algorithms used in Gretl? In other words, what references discuss in detail
how Gretl does what it does?
Tom
------------------------------
Message: 2
Date: Sun, 03 Feb 2008 18:31:32 +0100
From: Sven Schreiber <svetosch(a)gmx.net>
Subject: Re: [Gretl-users] Tests for Residuals
To: labone(a)gforcecable.com, Gretl list <gretl-users(a)lists.wfu.edu>
Message-ID: <47A5FA74.6080106(a)gmx.net>
Content-Type: text/plain; charset=ISO-8859-15; format=flowed
Am 03.02.2008 16:30, Tom La Bone schrieb:
> Good morning,
>
> 1) Does Gretl have tests for randomness of residuals accessible as options
> from the GUI?
>
> 2) From the command line?
Short answer: yes. Long answer: In contrast to some other open-source
projects, gretl has excellent documentation; I'm almost certain the user
guide has the detailed answers to your question.
>
> 3) What references are recommended for folks who interested in the
> algorithms used in Gretl? In other words, what references discuss in detail
> how Gretl does what it does?
>
Again, in some cases the documentation is fairly explicit, but
ultimately Allin and Jack would probably say: use the source, Luke.
(Nothing I ever do since I'm not literate in C, so I'm not trying to be
arrogant here, it's just the fact of open source that unlike proprietary
packages everything is accessible in principle.)
good luck,
sven
------------------------------
Message: 3
Date: Sun, 3 Feb 2008 13:00:05 -0500 (EST)
From: Allin Cottrell <cottrell(a)wfu.edu>
Subject: Re: [Gretl-users] Re: Unit Root Test
To: Gretl list <gretl-users(a)lists.wfu.edu>
Message-ID: <alpine.LRH.1.00.0802031228550.309(a)ricardo.ecn.wfu.edu>
Content-Type: TEXT/PLAIN; charset=US-ASCII
On Fri, 1 Feb 2008, Marcos Larios wrote:
> > could you be more specific, please? Single equation or VAR,
> > ARMA or not, etc. etc.
>
> Hi Sven, I'm refering to the Roots in an ARMA model, ...
At present the roots are computed and printed (as you know), but
they're not fetchable via a "$" variable. That probably should
be added.
In the meantime this might be helpful: if you estimate an ar(i)ma
model using the --x-12-arima option in gretl, a plain
text file named varname.rts (where "varname" is the name of the
dependent variable) is written. This is in a simple fixed format
and contains all the roots information. It will be written to
your x12arima working directory. You can find out where that is
using
print "@x12adir"
in gretl.
> the thing is that I need to build the graph for the unit root
> test in ARMA models, for which I require acces (through code) to
> the Roots, Imaginary, Modulus and Frecuency in the Unit Root
> Test Results in the ARMA models, I also need to know how to
> "draw" a circle in a graph with gretl, it seems I can't get
> gnuplot to recognize the circle equation...
We currently have code for graphing the roots when you estimate a
VAR. You can see how we do this in either of these ways.
(a) Estimate a arbitrary VAR in the GUI. In the VAR output window
select Graphs/VAR inverse roots. Click on the graph and select
"Save to session as icon". Open the icon view window (View/Icon
view). Right-click on the graph icon and select "Edit plot
commands". You'll get a window showing the gnuplot commands for
making this sort of graph, which you could save under another name
and use as a template.
(b) Look at the C code that constructs the graph commands for this
case.
http://gretl.cvs.sourceforge.net/*checkout*/gretl/gretl/lib/src/graphing....
and look for "gretl_VAR_roots_plot".
Allin Cottrell
------------------------------
Message: 4
Date: Sun, 3 Feb 2008 13:04:42 -0500
From: "Tom La Bone" <labone(a)gforcecable.com>
Subject: RE: [Gretl-users] Tests for Residuals
To: "'Sven Schreiber'" <svetosch(a)gmx.net>, "'Gretl list'"
<gretl-users(a)lists.wfu.edu>
Message-ID: <000401c8668f$41aaacc0$6401a8c0@Boozoo>
Content-Type: text/plain; charset="us-ascii"
Sven, thanks for your timely response.
In case I have not blown my cover already, I must confess that I am a stat
grad student taking his first time series course. Our professor has given us
the freedom to use any software we want for the course, and I am taking the
opportunity to learn Gretl. I chose Gretl because of many of the things you
mention, i.e., it is well documented, open source (I can look at the code if
I dare), and in the worst case it is a nice front-end for sending data to R
for further analysis.
The main downside of using Gretl is that nobody in the department is
familiar with the program so I am "on my own" in my efforts to learn how to
use it. I make an honest effort to look through the manual for answers to my
questions before asking for help. I have gotten some useful answers and
guidance that were not immediately obvious from the manual. On the other
hand I have gotten some guidance that goes into the "I have not gotten to
that chapter yet" bin. It would be helpful to be able to search the archives
for answers to my questions that have already been posted, but it appears
that is not possible.
In my question about documentation I guess I am asking if there is a
textbook that explains times series analysis as it is implemented in Gretl,
i.e., is there a times series textbook where the author planned on the
students using Gretl (like ITSM is used in Brockwell and Davis).
Tom
-----Original Message-----
From: Sven Schreiber [mailto:svetosch@gmx.net]
Sent: Sunday, February 03, 2008 12:32 PM
To: labone(a)gforcecable.com; Gretl list
Subject: Re: [Gretl-users] Tests for Residuals
Am 03.02.2008 16:30, Tom La Bone schrieb:
> Good morning,
>
> 1) Does Gretl have tests for randomness of residuals accessible as options
> from the GUI?
>
> 2) From the command line?
Short answer: yes. Long answer: In contrast to some other open-source
projects, gretl has excellent documentation; I'm almost certain the user
guide has the detailed answers to your question.
>
> 3) What references are recommended for folks who interested in the
> algorithms used in Gretl? In other words, what references discuss in
detail
> how Gretl does what it does?
>
Again, in some cases the documentation is fairly explicit, but
ultimately Allin and Jack would probably say: use the source, Luke.
(Nothing I ever do since I'm not literate in C, so I'm not trying to be
arrogant here, it's just the fact of open source that unlike proprietary
packages everything is accessible in principle.)
good luck,
sven
------------------------------
Message: 5
Date: Sun, 3 Feb 2008 16:47:34 -0500 (EST)
From: Allin Cottrell <cottrell(a)wfu.edu>
Subject: RE: [Gretl-users] Tests for Residuals
To: labone(a)gforcecable.com, Gretl list <gretl-users(a)lists.wfu.edu>
Message-ID: <alpine.LRH.1.00.0802031640270.309(a)ricardo.ecn.wfu.edu>
Content-Type: TEXT/PLAIN; charset=US-ASCII
On Sun, 3 Feb 2008, Tom La Bone wrote:
> In case I have not blown my cover already, I must confess that I
> am a stat grad student taking his first time series course. Our
> professor has given us the freedom to use any software we want
> for the course, and I am taking the opportunity to learn Gretl.
> I chose Gretl because of many of the things you mention...
OK, then we'll try to be extra-helpful ;-)
1) Does Gretl have tests for randomness of residuals accessible as
options from the GUI?
Yes, various aspects of the "randomness" (or otherwise) of the
residuals are explored by almost all the items under the "Tests"
menu in the model output window. You could also save the
residuals and do a runs test if you wanted.
2) From the command line?
help lmtest
help testuhat
help runs
3) What references are recommended for folks who interested in the
algorithms used in Gretl? In other words, what references discuss
in detail how Gretl does what it does?
The Gretl User's Guide, latest version at
http://ricardo.ecn.wfu.edu/pub/gretl/manual/
plus of course the C source, as Sven said.
Allin Cottrell
------------------------------
Message: 6
Date: Sun, 3 Feb 2008 21:15:41 -0500 (EST)
From: Allin Cottrell <cottrell(a)wfu.edu>
Subject: [Gretl-users] new string handling (was Re: Unit Root Test)
To: Gretl list <gretl-users(a)lists.wfu.edu>
Message-ID: <alpine.LRH.1.00.0802032105470.3269(a)ricardo.ecn.wfu.edu>
Content-Type: TEXT/PLAIN; charset=US-ASCII
On Sun, 3 Feb 2008, I wrote:
> In the meantime this might be helpful: if you estimate an
> ar(i)ma model using the --x-12-arima option in gretl, a plain
> text file named varname.rts (where "varname" is the name of the
> dependent variable) is written.
Around Christmas I added some functionality for handling strings.
I think the timing was bad and it wasn't much noticed, and as a
result was not much debugged. However, reading roots information
from a X-12-ARIMA .rts file is a handy case in point. I've had a
go at this, and in the process have fixed a few bugs and added
some more functionality. Find below a function that reads an .rts
file and returns a roots matrix. The new string-handling idioms
are explained in (a) "help sscanf" and (b) section 11.2 of the
User's Guide (CVS and Windows snapshot).
<script>
function read_x12a_roots (series y, int type[1:2:1])
# compose the name of the X12A roots file...
sprintf yfile, "%s/%s.rts", @x12adir, argname(y)
# and grab its content into a string
string rts = readfile(@yfile)
matrix r
matrix R
if (type = 1)
string targ = "AR"
else
string targ = "MA"
endif
string line = strstr(@rts, @targ)
loop while isstring(line) --quiet
# offset on line to find the numbers
string line = @line + 18
# get 4 values: real, imaginary, modulus, frequency
sscanf @line, "%m", r
R = R|r
string line = strstr(@line, @targ)
endloop
return matrix R
end function
open data9-7
arma 2 1 ; QNC --x-12-arima
AR_roots = read_x12a_roots(QNC, 1)
MA_roots = read_x12a_roots(QNC, 2)
print AR_roots MA_roots
</script>
Allin.
------------------------------
Message: 7
Date: Sun, 3 Feb 2008 21:51:24 -0500 (EST)
From: Allin Cottrell <cottrell(a)wfu.edu>
Subject: RE: [Gretl-users] Tests for Residuals
To: labone(a)gforcecable.com, Gretl list <gretl-users(a)lists.wfu.edu>
Message-ID: <alpine.LRH.1.00.0802032147370.3269(a)ricardo.ecn.wfu.edu>
Content-Type: TEXT/PLAIN; charset=US-ASCII
On Sun, 3 Feb 2008, Tom La Bone wrote:
> In my question about documentation I guess I am asking if there is a
> textbook that explains times series analysis as it is implemented in Gretl,
> i.e., is there a times series textbook where the author planned on the
> students using Gretl (like ITSM is used in Brockwell and Davis).
Try Lee Adkins's site:
http://www.learneconometrics.com/gretl.html
Allin Cottrell
------------------------------
Message: 8
Date: Mon, 04 Feb 2008 09:39:48 +0100
From: Sven Schreiber <svetosch(a)gmx.net>
Subject: Re: [Gretl-users] Tests for Residuals
To: Gretl list <gretl-users(a)lists.wfu.edu>
Message-ID: <47A6CF54.5080202(a)gmx.net>
Content-Type: text/plain; charset=ISO-8859-15; format=flowed
Am 04.02.2008 03:51, Allin Cottrell schrieb:
> On Sun, 3 Feb 2008, Tom La Bone wrote:
>
>> In my question about documentation I guess I am asking if there is a
>> textbook that explains times series analysis as it is implemented in Gretl,
>> i.e., is there a times series textbook where the author planned on the
>> students using Gretl (like ITSM is used in Brockwell and Davis).
>
> Try Lee Adkins's site:
>
> http://www.learneconometrics.com/gretl.html
>
Very interesting link; maybe worth adding it (or even an entire section
with related stuff) to the website, if it's not there already?
-sven
------------------------------
_______________________________________________
Gretl-users mailing list
Gretl-users(a)lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users
End of Gretl-users Digest, Vol 13, Issue 3
******************************************
16 years, 2 months
Gretl worth $4millon
by Talha Yalta
There is this nice website called Ohloh (http://www.ohloh.net), which
provides various metrics for open source projects. It is possible for
everybody to submit a project so that their source code crawler
monitors up-to-date development activity. Several weeks ago, I had
submitted gretl and today I noticed that they have finally processed
the data and prepared a report for our favorite econometrics program:
http://www.ohloh.net/projects/9753?p=gretl
Here are the main findings:
- Gretl is composed of a total of 297,477 lines of code.
- It would cost $4,274,252 to hire a team to write it from scratch.
- The source code is %77 C, %11 shell scripts and %10 XML.
- Among the 295 files in gretl, 252 are released under GPL 3.0 or
later, 23 are LGPL, 19 are GPL 2.0, and 1 is the New BSD license.
- Gretl's code base is mature and well established, however the source
code comments are relatively low
- Over the entire history of the project, 9 contributors have
submitted code. 4 have done so in the last year.
- Allin alone did about 90% of all commits over the 6.5 year existence of gretl.
As a user (and a minor contributor), I would like to thank Allin and
all developers for this excellent program. Keep up the good work!
Cheers
A. Talha YALTA
--
"Remember not only to say the right thing in the right place, but far
more difficult still, to leave unsaid the wrong thing at the tempting
moment." - Benjamin Franklin (1706-1790)
--
16 years, 2 months
(no subject)
by Mariusz Doszyń
Dear Gretl - users,
When I'm trying to do anything with gnuplot (edit, copy, ect) nothing is working properly and something like this happens: "C:\Program Files\gretl\wgnuplot.exe" "C:\userdata\gpttmp.a01256": exit code 1.
Do you know what's wrong?
Thanks for your help,
Best wishes,
Mariusz Doszyń
University of Szczecin,
Poland
16 years, 2 months
