Re: [Gretl-users] wishes list
by a b
Allin Cottrell a écrit :
On Fri, 1 Jun 2007, Hélio Guilherme wrote:
But we really need some more
gretlers who are in a position to make the gretl wish list
_shrink_! (That is, by implementing some of the items on the
list.)
If you know of any graduate students with programming expertise
who might be interested in contributing to gretl, please try to
encourage them to do so!
I have no grasp on C programming but I used to program in Visual Basic a (rudimenatry) econometric software that I went proud of. I gave up when I knew about Gretl! Anyway, could you or anyone else recommand me any good book on C/C++ programming (in english, french or italian) or any other web resources, it should be a pleasure to invest my spare time (and much more than that) to be of any help in contributing to Gretl! It really deserves it!
Thanks once again, for having offered us a useful and great softawre!
Artur
---------------------------------
Stockage illimité de vos mails avec Yahoo! Mail. Changez aujourd'hui de mail !
18 years, 8 months
fonts and colors in saved plot
by Sven Schreiber
Hi,
I'm experiencing a problem when saving a plot to pdf or eps. (As opposed
to saving to the symbol table which works fine.) The problem is that I
have manually increased the font size, but that doesn't carry over to
the file. Also, the default colors blue and red which gretl uses for the
two series are fine in the plot window, but in the file the blue has
turned to green.
Anything I can do to get plots in pdf or eps with larger fonts?
thanks,
Sven
18 years, 10 months
Re: [Gretl-users] Re: Scatterplot and gnuplot 4.3
by Secchi Angelo
On Thu, 26 Jul 2007 17:01:14 -0400 (EDT)
Allin Cottrell <cottrell(a)wfu.edu> wrote:
> On Thu, 26 Jul 2007, I wrote:
>
> > > set missing "?"
> > > ^
> > > ".../gretl/gpttmp.VsvKxg", line 7: valid set options: [] =
> > > choose one, {} means optional
> >
> > That's gnuplot compaining, not gretl itself. This would appear to
> > be a backward-incompatible change of syntax in gnuplot 4.3.
>
> Yes, it is. I notice, however, that you can configure the gnuplot
> build with
>
> --enable-backwards-compatibility
>
> I've attempted to work around this particular issue in gretl CVS,
> but there may be other similar issues lurking.
Works. Thank you very much.
Angelo
>
> Allin.
> _______________________________________________
> Gretl-users mailing list
> Gretl-users(a)lists.wfu.edu
> http://lists.wfu.edu/mailman/listinfo/gretl-users
--
========================================================
Angelo Secchi PGP Key ID:EA280337
========================================================
Research Fellow Scuola Superiore S.Anna
Piazza Martiri della Liberta' 33, Pisa, 56127 Italy
ph.: +39050883365 fax: +39050883344
email: secchi(a)sssup.it www.sssup.it/~secchi/
========================================================
18 years, 10 months
Re: [Gretl-users] Spearman Rank correlation
by Secchi Angelo
On Thu, 26 Jul 2007 16:26:13 -0400 (EDT)
Allin Cottrell <cottrell(a)wfu.edu> wrote:
> On Thu, 26 Jul 2007, Angelo Secchi wrote:
>
> > Now it seems ok, thanks. I checked also the test and I have a
> > couple of doubts:
> >
> > 1. There something I do not understand in p-values. I believe
> > you used the Normal approximation (instead of Student-T) because
> > of ties. Am I right? Still the value obtained are significantly
> > different from the ones obtained in R and Stata and I do not
> > believe it is an approximation issue...
>
> Yes, I was using (possibly mis-using) the normal approximation. I
> have now changed this to use the t-approximation when there are
> ties.
>
> t(n - 2) = rho / sqrt((1 - rho) * (1 - rho) / (n - 2))
>
> See what you think.
Thanks, it seems ok now. I will do some more detailed
exploration
in the next few days and, in case, I will provide you with
new
feedback. Just a small detail: I believe it would be nice
to make users
able to easily generate a scatter plot with the two series
of ranks
generated for the test, if it is not too much work.
Thanks again,
Angelo
>
> > 2. If I may, I would suggest to implement as default a two
> > tailed alternative. In general this test is considered to verify
> > the presence of correlation between two samples independently
> > from its sign.
>
> Yes, that's a good idea.
>
> Allin.
> _______________________________________________
> Gretl-users mailing list
> Gretl-users(a)lists.wfu.edu
> http://lists.wfu.edu/mailman/listinfo/gretl-users
--
========================================================
Angelo Secchi PGP Key ID:EA280337
========================================================
Research Fellow Scuola Superiore S.Anna
Piazza Martiri della Liberta' 33, Pisa, 56127 Italy
ph.: +39050883365 fax: +39050883344
email: secchi(a)sssup.it www.sssup.it/~secchi/
========================================================
18 years, 10 months
Scatterplot and gnuplot 4.3
by Allin Cottrell
Angelo wrote:
> while exploring Rank correlation I've noticed that the command
> "XY Scatterplot" does not work properly at least on my computer
> (gentoo amd64, with gnuplot 4.3 cvs-updated).
> If I try to do a scatterplot either with the "right click" menu
> in the main window or with "View>Graph Specified Vars>X-Y
> scatter" I get a segmentation fault with Gretl complaining about
> set missing "?"
> ^
> ".../gretl/gpttmp.VsvKxg", line 7: valid set options: [] =
> choose one, {} means optional
That's gnuplot compaining, not gretl itself. This would appear to
be a backward-incompatible change of syntax in gnuplot 4.3.
Bother. I'll have to install 4.3 and investigate.
Allin.
18 years, 10 months
Spearman Rank correlation
by Angelo Secchi
Hi,
I've noticed a strange behaviour of GRETL with Rank Correlation. I
tried to get the value of the Spearman \rho with two series of about
15000 obs and I got \rho=-2038.292267 (???).
If I do the same with R(even launched inside GRETL) or Stata I get a
more reasonable 0.5715.
Am I missing something? How is the Spearman's \rho defined in Gretl?
Thanks,
Angelo
--
========================================================
Angelo Secchi PGP Key ID:EA280337
========================================================
Research Fellow Scuola Superiore S.Anna
Piazza Martiri della Liberta' 33, Pisa, 56127 Italy
ph.: +39050883365 fax: +39050883344
email: secchi(a)sssup.it www.sssup.it/~secchi/
========================================================
18 years, 10 months
Scatterplot
by Angelo Secchi
Hi,
while exploring Rank correlation I've noticed that the command "XY
Scatterplot" does not work properly at least on my computer (gentoo
amd64, with gnuplot 4.3 cvs-updated).
If I try to do a scatterplot either with the "right click" menu in the main window or with
"View>Graph Specified Vars>X-Y scatter" I get a segmentation fault with
Gretl complaining about
set missing "?"
^
".../gretl/gpttmp.VsvKxg", line 7: valid set options: [] = choose one, {} means optional
Strangely enough if I do the same with the "View>Multiple Graph"
I get the correct plot.
Angelo
--
========================================================
Angelo Secchi PGP Key ID:EA280337
========================================================
Research Fellow Scuola Superiore S.Anna
Piazza Martiri della Liberta' 33, Pisa, 56127 Italy
ph.: +39050883365 fax: +39050883344
email: secchi(a)sssup.it www.sssup.it/~secchi/
========================================================
18 years, 10 months
Loop problems
by Johannes Fichtinger
Hello everyone,
first of all, thank you a lot for that great piece of software!
Now, I have some questions regarding the use of loops in gretl. I have some
many datasets in one gretl file like x1 y1 x2 y2 x3 y3 ... x80 y80, where x-y
stands for a pair of variables such that e.g. x1 is the independent,
explanatory variable of y1, x2 explains y2 and so on.
1. First, I would like to run in a script a simple regression like:
loop i=1..80
ols $i+1 const $i
endloop
where $i+1 should be replaced in the loop with the variable y1 and $i with x1.
Obviously, this is not working. I tried many different possibilities, but i
did not found a solution. My problem: the variables are not really named like
x1, y1 ..., so i can simply copy the example 9.5 in the user guide (May 2007)
on page 55, but i need a way to access the variables by its id number and not
the name. How can i do this?
2. Is it possible to run in a loop smth like
loop i=1..80
gnuplot $i
endloop
If I try this, he complains that the command gnuplot is not available in loop
mode. This brings me to my last question:
Why are some commands not available in loop mode? This behaviour was somehow
surprising for me.
Thanks,
Johannes.
18 years, 10 months
Cochrane Orcutt: help!
by Giovanni Inglisa
Hi all! I'm not sure this is the most appropriate way to ask for
support...but...here are my doubts
I'm estimating AR parameters + a constant with a Cochrane-Orcutt
alghorithm, which is the same used by the AR estimate procedure in gretl.
Unfortunately I get really different values with respect to the
constant, while the coefficients for the lagged variables are almost
equal (and these coefficients are the same as those which result form
the OLS regression of Y over const+lags) . Is it possible that gretl is
not just using the cochrane alghoritm but something more sophisticated?
Or maybe it doesnt'build the regressosr matrix as I do: the constante
vector + the three arrays of lagged variables.
Does any of you have an idea? I spent all the day writing this cochrane
code and I didn't gain any improvement :-((
Thank you
Giovanni
18 years, 10 months
