on gretl's menu
by artur bala
Hi,
Just wanted to share 2 ideas about gretl's menu:
1. why does the <Rank Correlation> command come under the <Model ->
Robust Estimation> menu ? It seems a little bit counterintuitive,
doesn't it? correlation is much more descriptive rather than a model.
2. should the <Variable> menu switch to active even though 2 (or more)
variables are selected in gretl's main window, shouldn't it? Indeed, a
lot of its sub-menus (summary statistics, tests, plots,...) do make sens
for a multiple variable choice as well.
cheers,
artur
16 years
urgent emergency problem
by Franck Nadaud
Greetings from Paris !
Ouch... I'm got a dirty problem:
it seems that my data file has been damaged: when i try to open it right now,
gretl says in a not very funny way:
"failed to parse data at observation 2329"
and get stuck there... How may I repair that ?
I tried to use the bacukup .gtd~ file but same punishment...
I tried to get back to 1.8.7 with the same results, so it is not 1.9.0. that
poses problems, but maybe my datafile is corrupted...
So ?
all this seems to be badly engaged. All runned ok for weeks and...
Too bad I have important work to finish right now of course...
Well, i am beginning to reprocess and reprepare all my data...
well, cheers
sincerely
F.
--
Franck Nadaud
CIRED
UMR 8568 CNRS - EHESS, ENPC, ENGREF, CIRAD
45 bis avenue de la Belle Gabrielle
94736 Nogent-sur-Marne Cedex
TEL: 33-1-43-94-73-94
FAX: 33-1-43-94-73-70
MOB: 06-07-39-92-75
France
16 years
errors in building gretl on Windows xp
by RAZIA HAIDER
Hi,
I am using Windows XP (64 bit). I want to build gretl on windows.
After downloading and installing MinGW and MSYS I downloaded and installed
the all-in-on bundle of GTK+ for win64 on
http://ftp.acc.umu.se/pub/gnome/binaries/win64/gtk+/2.20/
then installed all files from
http://ricardo.ecn.wfu.edu/pub/gretl/winbuild/ and follow the instructions
given in NOTE file
there.
When typing "make" in c:\gretl\win32 got the following output with errors,
how to solve it???
/bin/sh: pkg-config: command not found
/bin/sh: pkg-config: command not found
/bin/sh: pkg-config: command not found
gcc -Wall -O2 -mms-bitfields -DWIN32 -Wall -o builddate ../builddate.c
./builddate
build.h is current
mkdir -p dlls
mkdir -p plugins
mkdir -p import-libs
gcc -Wall -O2 -mms-bitfields -DWIN32 -c -I. -I../lib/src -I../plugin
-I../gui2 -Ic:/mingw/include/libxml2 -I../plugin/zipunzip
-I/opt/R/lib/R/include -DUSE_GMP ../lib/src/csvdata.c
../lib/src/csvdata.c:27:18: glib.h: No such file or directory
../lib/src/csvdata.c: In function `utf8_ok':
../lib/src/csvdata.c:1086: warning: implicit declaration of function
`g_utf8_validate'
../lib/src/csvdata.c: At top level:
./lib/src/csvdata.c:1827: error: syntax error before '*' token
../lib/src/csvdata.c: In function `label_is_valid':
../lib/src/csvdata.c:1829: error: `s' undeclared (first use in this
function)
../lib/src/csvdata.c:1829: error: (Each undeclared identifier is reported
only once
../lib/src/csvdata.c:1829: error: for each function it appears in.)
../lib/src/csvdata.c:1832: warning: implicit declaration of function
`g_utf8_strlen'
../lib/src/csvdata.c:1833: error: `gunichar' undeclared (first use in this
function)
../lib/src/csvdata.c:1833: error: syntax error before "u"
../lib/src/csvdata.c:1836: error: `u' undeclared (first use in this
function)
../lib/src/csvdata.c:1836: warning: implicit declaration of function
`g_utf8_get_char'
../lib/src/csvdata.c:1840: warning: implicit declaration of function
`g_utf8_next_char'
../lib/src/csvdata.c: In function `real_read_labels_and_data':
../lib/src/csvdata.c:1894: error: `gchar' undeclared (first use in this
function)
../lib/src/csvdata.c:1894: error: syntax error before ')' token
../lib/src/csvdata.c:1897: error: syntax error before "else"
../lib/src/csvdata.c: At top level:
../lib/src/csvdata.c:1906: error: syntax error before "if"
../lib/src/csvdata.c:1914: warning: type defaults to `int' in declaration of
`err'
../lib/src/csvdata.c:1914: error: `drop' undeclared here (not in a function)
../lib/src/csvdata.c:1914: error: `c' undeclared here (not in a function)
../lib/src/csvdata.c:1914: error: initializer element is not constant
../lib/src/csvdata.c:1914: warning: data definition has no type or storage
class
../lib/src/csvdata.c:1915: error: syntax error before '}' token
../lib/src/csvdata.c: In function `csv_parsing_header':
../lib/src/csvdata.c:1942: error: `gchar' undeclared (first use in this
function)
../lib/src/csvdata.c:1942: error: `trfname' undeclared (first use in this
function)
../lib/src/csvdata.c:1942: warning: implicit declaration of function
`g_locale_to_utf8'
../lib/src/csvdata.c:1945: warning: implicit declaration of function
`g_free'
make: *** [csvdata.o] Error 1
Need urgent help.
Thanks!
Haider.
16 years
configure:error can't find a definition of inet-addr
by RAZIA HAIDER
Hi,
I am trying to build gretl on windows xp(64-bit). I followed all steps
written in README.native file.
i have following problems:
1. I did not find "*winbuild* *folder"* in "*MinGW folder"* (but i have put
required files in "*mingw32 folder"*, (i dnt knw is it right?))
2. And then when I use *MSYS*, I changed my directory to *gretl source
directory*
3. Finally when I write *./configure* command i got error *"configure:error
can't find a definition of inet-addr",* i do not know what is this ( I am
working first time with MinGW or MSYS).
Please help me in this regard. what should i do to compile gretl code.
Thanks in advance.
Ciao!
Haider
--
Razia Haider
Ph.D. student
Dipartimento di Ingegneria dell'Informazione
Universita' di Modena e Reggio Emilia
Via Vignolese 905, 41100 Modena, Italy
e-mail: razia.haider(a)unimo.it
tel: +39 059 2056314
16 years
estimating discrete choice models
by Petr Mariel
Walt,
you are probably speaking about Discrete Choice Models based on the McFadden
Random Utility Models.
These models are not implemented in gretl.
You can estimate them in
STATA or Nlogit (retail software)
R or Biogeme (open source)
See
http://www.youtube.com/watch?v=F1Zj7W_z8yk
how to estimate Discrete Choice Models in Stata and R
--
Petr Mariel
Departamento de Econometría y Estadística
UPV, Facultad de Ciencias Económicas y Empresariales
Avda. Lehendakari Aguirre 83
E48015 BILBAO, SPAIN
e-mail: Petr.Mariel(a)ehu.es
Tel.: +34.94.601.3848 Fax.: +34.94.601.3754
--------- Mensaje reenviado --------
De: Sven Schreiber <svetosch(a)gmx.net>
Reply-to: Gretl list <gretl-users(a)lists.wfu.edu>
Para: walt(a)dataanalyticscorp.com
Cc: Gretl list <gretl-users(a)lists.wfu.edu>
Asunto: Re: [Gretl-users] estimating discrete choice models
Fecha: Mon, 17 May 2010 14:29:07 +0200
Data Analytics Corp. schrieb:
> Hi Sven,
>
> Thanks for the advice, but the problem for a stated preference discrete
> choice model is that estimation depends on the choice sets seen by the
> individuals. Say each individual sees a choice set with three
> alternatives. The estimation routine needs to know the three and which
> of the three was selected. STATA allows this. I don't see that here.
>
Well if the three alternatives are different from one observation to the
next (why are they always three then, though?), this is beyond me,
sorry. Probably not doable in gretl (apart from programming it up
yourself with gretl's scripting language, of course...).
good luck,
sven
_______________________________________________
Gretl-users mailing list
Gretl-users(a)lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users
16 years
estimating discrete choice models
by Data Analytics Corp.
Hi,
Can a stated preference discrete choice model (especially one with a
None or base alternative) be estimated in Gretl? If so, how?
Thanks,
Walt
________________________
Walter R. Paczkowski, Ph.D.
Data Analytics Corp.
44 Hamilton Lane
Plainsboro, NJ 08536
________________________
(V) 609-936-8999
(F) 609-936-3733
walt(a)dataanalyticscorp.com
www.dataanalyticscorp.com
_____________________________________________________
--
________________________
Walter R. Paczkowski, Ph.D.
Data Analytics Corp.
44 Hamilton Lane
Plainsboro, NJ 08536
________________________
(V) 609-936-8999
(F) 609-936-3733
walt(a)dataanalyticscorp.com
www.dataanalyticscorp.com
16 years
creating ID variables
by Data Analytics Corp.
Hi,
Suppose I have a data set of 200 cars where the observation labels are
the make (Chevy, Honda, BMW, etc.). Say there are 10 makes. I want to
create a variable, say ID, that identifies the make so I don't have to
rely on the observation label. The purpose is to later create dummies
for the makes to include in a regression model and create boxplots (one
for each make's price, all shown in one plot window) of price. How can
I do this? Or is it better to just use the observation labels and
laboriously write if statements?
Thanks,
Walt
________________________
Walter R. Paczkowski, Ph.D.
Data Analytics Corp.
44 Hamilton Lane
Plainsboro, NJ 08536
________________________
(V) 609-936-8999
(F) 609-936-3733
walt(a)dataanalyticscorp.com
www.dataanalyticscorp.com
_____________________________________________________
--
________________________
Walter R. Paczkowski, Ph.D.
Data Analytics Corp.
44 Hamilton Lane
Plainsboro, NJ 08536
________________________
(V) 609-936-8999
(F) 609-936-3733
walt(a)dataanalyticscorp.com
www.dataanalyticscorp.com
16 years
feature request
by Lars Pålsson-Syll
Hi,
Via gretl I can access the "paired samples t-test" (aka "dependent t-test") in R. Since gretl already has the "independent t-test" in
the Test statistic calculator I think it would be nice also to be able to perform the "paired samples t-test" without having to open
up R.
Best regards,
Lars
------------------------------
_______________________________________________
Gretl-users mailing list
Gretl-users(a)lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users
End of Gretl-users Digest, Vol 40, Issue 12
*******************************************
Lars Palsson Syll
Professor of Civics
Malmo University
Sweden
16 years
Question regarding function output
by Artur T.
Hi gretl community,
I programmed a function which gives an output of transformed variables
defined in a list. Actually I would like to add this output as newly
generated series to the current variables.
The function is given by:
--------------------------------------------------------------------------
function list Regime_Series (list Y "List of variables")
smpl --full
loop foreach i Y --quiet
series pd_d_$i = 0 #Generate series for positive changes
series nd_d_$i = 0 #Generate series for negative changes
endloop
list dY = diff(Y) #1st difference of Y
#attribute the first differences to the series
loop foreach i dY --quiet
smpl $i > 0 --restrict #Restrict positive changes
pd_$i = $i #Generate series of positive changes
smpl --full
smpl $i < 0 --restrict #Restrict negative changes
nd_$i = $i #Generate series of negative changes
smpl --full
endloop
# create partial sum process
loop foreach i Y --quiet
series $i_p = 0
series $i_m = 0
series $i_p = $i_p(-1) + pd_d_$i #Partial sum process of positive
changes
series $i_m = $i_m(-1) + nd_d_$i #Partial sum process of negative
changes
endloop
end function
----------------------------------
I would like to add the series $i_p and $i_m to the current variables
but I cannot find out how to use the "return" command correctly in this
context. Does anybody have a suggestion?
Thanks in advance!
Artur
16 years, 1 month
error message:criterion is not met a warning
by RAZIA HAIDER
Hi everone,
I am new to gretl, i want to use its MLE for estimation. I have written
small script just to check that how MLE works but i have following error
message (criterion is not met a warning ). I have used sample data set data
2-1.gdt. here is my scrpit.
genr pi=3.14
scalar a=2*pi
scalar mu=1
scalar sigma=1
series s=sigma^2
sereis sq=2*s
series s3=sigma^3
scalar sq3=2*s3
series c=vsat-mu
series sq1=c^2
mle logl=-0.5*log(a)-log(sigma)-(sq1/sq)
deriv mu=-c/s
deriv sigma=-1/sigma + (sq1/s3)
end mle
i do not know where is the problem
and if I use this code then i have error message that "*failed to invert OPG
matrix GG'"*
genr pi=3.14
scalar a=2*pi
scalar mu=1
scalar sigma=1
series s=sigma^2
sereis sq=2*s
series s3=sigma^3
scalar sq3=2*s3
series c=vsat-mu
series sq1=c^2
mle logl=-0.5*log(a)-log(sigma)-(sq1/sq)
params mu sigma
end mle
or if i add at last
end mle --hessian
error message will be "*numerical hessian is not computable*"
Can anyone tell me about this error or how to solve it??
Thanks in advance.
--
Haider
16 years, 1 month
