Current gretl CVS and the Windows snapshot at
contain release candidate 1 for gretl 1.7.6.
Please note that this version involves a backward-incompatible
change with respect to gretl 1.7.5 and earlier, affecting
user-defined functions that (a) take a named list of variables as
an argument and (b) do things with the list-member variables by
means of a "foreach" loop on the list.
I won't go into the rationale for this change here. Anyone who
wants the details may look at the proceedings on the gretl-devel
list for July, which were mostly taken up with this issue:
There's also a brief discussion in the chapter of the User's Guide
that deals with user-defined functions. But here's the bottom
line for users:
* If you want to "get hold of" a list-member variable in the
context noted above, you have to use the syntax listname.varname,
where listname is the name of the list in question and varname is
the name of the list member. (This is required only if you're
working with a list that was supplied as a function argument.)
Trivial example: inside a function, creating new variables which
are the cubes of the members of an original list, xlist, where
xlist is an argument to the function.
loop foreach i xlist
$i_3 = $i^3
loop foreach i xlist
$i_3 = (xlist.$i)^3
In the new scheme, "$i" gets the name of the list-member variable
alright, but the variable is not "visible" under that name within
the function. So on the right-hand side of the expression that
creates the cubes, we need "(xlist.$i)^3". (Well, actually the
parentheses are not required, but wearing your seatbelt is in
general a good idea.)
Although this may affect quite a large number of existing
functions, we believe the effects are localized and the update
should be trivial. If anyone has a function for which the update
is _not_ trivial, please let us know.
I sent a mail for our gretl list speaking about my problems with
accented filenames. Well, I hadn't solved my problem yet. Because of this I
try to use a PC (with Windows XP) computer to avoid these problems. But
another problem had arised!
I going to describe the problem to you with details:
(1) I opened gretl (version 1.7.8cvs build date 2008-09-22)
(2) I opened the datafile called "data9-7.gdt" (from the Ramanathan's
(3) I saved these file with another name: "Acentuação.gdt"
(4) I closed gretl
(5) I opened gretl again clicking in "Acentuação.gdt" twice
(6) I deleted the series 9, 10 and 11 (named SPRING, SUMMER and FALL,
(7) I saved the database with these changes and closed gretl*
*After the "step 7", described above, I`d noticed that a new file, called
"Acentuação.gdt~" had appeared in the same folder of the file
"Acentuação.gdt". Before proceeding I had deleted this new file
(8) I opened gretl again with a double click in the file "Acentuação.gdt"
(9) I opened the series called PRICE and choose the option "graph"
(10) I saved the graph as a session icon
(11) I closed the graph and tried to save the session with the name
"Acentuação Session.gretl". In that point the following message appears:
"zip error: File not found or no read permission (file '.Acentuação Session'
was not found)"
(12) After that message I tried to save the session with the name
"Acentuacao Session.gretl" (without accented characters). The software
(gretl) saved the session with success with the name "Acentuacao
(13) I closed gretl and when I'd tried to open the session file called
"Acentuacao Session.gretl"the following message appears:
"No such file or directory"
What's wrong? Am I doing any mistake? Any help are welcome!
PS.: I know I'm bugging you guys, but it isn't my intention! Sorry! :(
Dear Allin & all
Thanks for your great job in building this software. I am trying to
translate gretl into Traditional Chinese. What are the files (for
example, gretl.mo) you needed to be attached in the gretl official
I've done the translation of the menu and dialog box and tested it
both in winxp, win2000, ubuntu (7.x, 8,x). They all look fine without
any modification on the OS's font settings.
But it seems that Tradition Chinese characters in the output and
gnuplot needs specific fonts (rather than the default installed fonts)
to be shown correctly. That is, the default font in windows "Courier
New" does not work for Traditional Chinese. Users have to change the
fixed font to, e.g., MS Gothic.
Does the translation of other lanaguages encounter the similar
problems, and how does this can be solve? I mean that after
installation, do the users have to change the fixed font setting
themselve (as well as to set the environmental variable, set LANG=tw,
in windows) when they try to use the locale *.mo in order to show
Chung Yuan Christian University
I hope someone can help me..
When I run a fixed and random effects model for my data, I obtain very differing results my variable of interest when using time dummies or a continuous year variable.. When I use a year variable my variable of interest (AS5) is only just insignificant (p=0,15) nut when I use time dummies it is totally insignificant (p=0,73). The hausman test is also inconclusive when I use the year variable, but points towards fixed effects when using time dummies.
When I insert an interaction term between AS5 and MW (another variable already in the model), both the interaction term and AS5 become significant when using the year variable, but only the interaction term becomes significant when using time dummies.
The outputs are attached to the mail.. Can someone explain to me what causes the differences and what I am to do next..
Thanks from a newby..
What can you do with the new Windows Live? Find out
(Sorry for the cross-posting to the two lists, but I wanted to
make sure I got everyone).
We're now close to the point of releasing gretl 1.8.0, having
assembled quite a few new features and a lot of bug fixes.
See http://gretl.sourceforge.net/ChangeLog.html .
But the most exasperating thing in this business is when you make
a new release and immediately get a report of a serious bug and so
have to make a further release right away.
In this regard, everyone can help. The Windows snapshot, at
and the OS X (Intel) snapshot, at
are both up to date with gretl CVS as of January 12.
If you can find 15 minutes to run your favourite gretl scripts, or
try your favourute gretl GUI operations, then please do, and
report any problems on one or other of the mailing lists.
If any errors come up, we'll fix them tout de suite, then make
gretl 1.8.0 available. Also, if any translators have things they
want to update for the forthcoming release, please do that in the
next day or two. Thanks!
Department of Economics
Wake Forest University
Hello users of the translated German gretl interface,
in case you didn't know, I'm the German translator. I have just updated
the keyboard shortcuts for many menu items. (We're talking about the
underscore you see under a letter of a menu entry. Pressing Alt+[the
underscored letter] activates the menu item.) Of course, this does *not*
affect the released version 1.8.0, but all snapshots and releases from
Quite a few keyboard shortcuts were added, but some have also been
rearranged and changed in order to avoid ambiguities and multiple key
assignments. That means that maybe some of your favorite keyboard
shortcuts won't work anymore and you have to get used to new ones. I
hope the re-learning costs are not too high and that the benefit of more
keyboard shortcuts outweighs the adjustment cost both in the long and
the short runs.
Actually, it could be that some more changes will be applied before
version 1.8.1 is released. But that of course would only matter for
users of the interim snapshots or cvs delevopment versions.
1. I use the command, gnuplot as follows
gnuplot x1 x2 y1 y2 --time-series --with-lines
without any problems. What should I do if I would like to draw x1 x2
with lines but y1 y2 with points?
2. The command, gnuplot, in console can generate a plot. But it seems
not to work when I use the same gnuplot command in a script. It
responds that, for example,
Is this normal? How can I access (open) *.plt files?
I am trying to run a Goldfeld-Quandt and to do that I need to sort all the observations according to one of the explanatory variables.
Can someone say how I can do that?
(I tried running multiple sortby but this is quite labor intensive and very very error sensitive)
I´m a student and currently working on my masters thesis to conclude my accountancy study.
My question regards the use of OLS and GLS. I have a large panel data collection, consisting of about 1500 firms, with observations over max. 3 years. So OLS regression is bound to lead to biased errors, since the data have both time series and cross sectional dimensions. Therefore, I have estimated the model using the random effects GLS method, and the model seems to be valid. At the bottom of this mail I included the results.
There is however no Rsquare (or equivalent number) available in the output. Is it possible to obtain such a number for GLS?
On page 111 and 112 of the instruction manual, it states that GLS is equivalent to OLS using quasi demeaned variables. I don't completely understand the formula however. To obtain the fraction by which the variables should be demeaned, the between and within variances should be filled in to the formula. The Ti in the formula, does it refer to the total number of observations used to construct the model? (I have a total of 2689 firm year observations, so Ti = 2689??).
If the variable observations are demeaned by the calculated fraction of the mean of that variable, can I then use these new variables to construct an OLS model which is reliable, and thus obtain a Rsquare? Or is there a simpler way of obtaining a figure stating the the explanatory power of my model?
Thanks for the help! Dennis
Output of GLS regresion:
Model 8: Random-effects (GLS) estimates using 2689 observations
Included 1290 cross-sectional units
Time-series length: minimum 1, maximum 3
Dependent variable: LNFEE
Mean of dependent variable = 13,3439
Standard deviation of dep. var. = 1,20651
Sum of squared residuals = 906,323
Standard error of the regression = 0,584044
'Within' variance = 0,115462
'Between' variance = 0,30521
Akaike information criterion = 4772,68
Schwarz Bayesian criterion = 4967,28
Hannan-Quinn criterion = 4843,07
Breusch-Pagan test -
Null hypothesis: Variance of the unit-specific error = 0
Asymptotic test statistic: Chi-square(1) = 485,572
with p-value = 1,30992e-107
Hausman test -
Null hypothesis: GLS estimates are consistent
Asymptotic test statistic: Chi-square(15) = 113,98
with p-value = 2,76456e-017
Test for normality of residual -
Null hypothesis: error is normally distributed
Test statistic: Chi-square(2) = 339,203
with p-value = 2,20321e-074
Express yourself instantly with MSN Messenger! Download today it's FREE!
I'm trying to master Johansen's test for cointegration, but I am a bit
puzzled. When I ran a bivariate Johansen test on some data I'm working on,
the result was:
Case 3: Unrestricted constant
Rank Eigenvalue Trace test p-value Lmax test p-value
0 0,21652 20,783 [0,0062] 14,153 [0,0502]
1 0,10802 6,6300 [0,0100] 6,6300 [0,0100]
(Two time series of 60 observations each. ADF, PP and KPSS tests indicate
that they both are I(1). )
As I've understood it, this means that the test rejects both the "no
cointegrating equation" and the "one cointegrating equation" hypotheses, but
there can't be two cointegrating relations with only two variables, right?
Could there be some sort of misspecification issue (e.g. wrong lag length)