logit model - f(beta'x) at mean of independent vars
by Katrin Woelfel
Dear Gretl community,
When working with a logit model (binary) in GRETL, I wondered about the
number of "f(beta'x) at mean of independent vars" in the output.
Can anybody tell me, how this value is computed?
Thanks a lot in advance.
Regards,
Katrin
13 years, 9 months
Accessing the critical values of the Johansen coint. test
by artur tarassow
Hi gretl community,
I would like to compute Johansen's coint. test recursively and
normalize the obtained Trace statistics by the 1%, 5 and 10% critical
values (small sample adjusted). Normally I use the critical values
taken from Peseran et al. for this, but I wondering whether I can
access gretl internal critical values instead.
Best,
Artur
13 years, 9 months
addlist script improvement for OLS...is possible?
by alberto.cavalli＠unifi.it
I would like to know if it is possible to plan an improvement of the
script addlist: sequential addittion of variables to a model made by
Allin Cottrell.
Now the script return the best combination of regressors on the bae of
AIC. It coluld be useful to print all the combinations between
regressor in order for a better evaliation of the regressor (in same
cases). I thing that an array could be used in order to move the
regressors from one list1 to list0 and, in a loop print the results of
OLS. Unlikely I'm not so expert and I'm not able to create the correct
array. Any suggest will be appreciated
Thanks in advance
alberto
13 years, 9 months
Storing the loadings of principal component analysis
by amaryl
Dear all,
is there a way to store the component loadings as a matrix after doing a
principal component analysis? I get the loadings as output, of course,
but I need them for further processing.
Thanks in advance!
13 years, 9 months
Re: [Gretl-users] maybe it´s a bug...
by Allin Cottrell
On Fri, 10 Jun 2011, =?ISO-2022-JP?B?Q2xhdWRpbyBTaGlraWRhICgbJEJJX0VEPCNAPyEhJS8laSUmJTglKhsoQik=?= wrote:
> Ok, Thanks again, Allin.
I found the problem. I didn't see it at first because it's
specific to annual data and I was testing on quarterly data.
Anyway, thanks for the report and this should now be fixed in CVS
and snapshots.
(The problem: the ADF test in the gretl GUI, with annual data, (a)
showed the quadratic trend option as disabled, but (b) in fact
included this test option regardless of what was selected.)
Allin Cottrell
13 years, 9 months
Re: [Gretl-users] maybe it´s a bug...
by Allin Cottrell
On Thu, 9 Jun 2011, =?ISO-2022-JP?B?Q2xhdWRpbyBTaGlraWRhICgbJEJJX0VEPCNAPyEhJS8laSUmJTglKhsoQik=?= wrote:
> I just recorded all the procedure, in a short avi movie. If you
> want to see it, just give an email address (I don´t know if
> it´s appropriate to send it in this list) and I send it to you.
> It´s really strange, like a small bug.
Thanks. Let me look at the code some more and see if I can provoke
the problem. I may ask you for the avi file if I still can't
replicate it -- but you're right, such files are not appropriate
for the list.
Allin Cottrell
13 years, 9 months
Re: [Gretl-users] maybe it´s a bug...
by Allin Cottrell
On Thu, 9 Jun 2011, =?ISO-2022-JP?B?Q2xhdWRpbyBTaGlraWRhICgbJEJJX0VEPCNAPyEhJS8laSUmJTglKhsoQik=?= wrote:
> It�s just to check. I was just using a regular time series analysis and
> every time I ask for an ADF test for any series, clicking "only constant", I
> have, as an output, this specification but also the "constant and quadratic
> trend".
What version of gretl are you using, on what platform? I'm not
able to replicate this with current gretl.
Allin Cottrell
13 years, 9 months
maybe it´s a bug...
by Claudio Shikida (敷田治誠 クラウジオ)
Hi to all,
It´s just to check. I was just using a regular time series analysis and
every time I ask for an ADF test for any series, clicking "only constant", I
have, as an output, this specification but also the "constant and quadratic
trend".
Is this a bug?
Thanks for your time and attention and sorry for any stupid question.
Claudio
--
http://www.shikida.net and http://works.bepress.com/claudio_shikida/
Esta mensagem pode conter informação confidencial e/ou privilegiada. Se você
não for o destinatário ou a pessoa autorizada a receber esta mensagem, não
poderá usar, copiar ou divulgar as informações nela contidas ou tomar
qualquer ação baseada nessas informações. Se você recebeu esta mensagem por
engano, por favor avise imediatamente o remetente, respondendo o presente
e-mail e apague-o em seguida.
This message may contain confidential and/or privileged information. If you
are not the addressee or authorized to receive this for the addressee, you
must not use, copy, disclose or take any action based on this message or any
information herein. If you have received this message in error, please
advise the sender immediately by reply e-mail and delete this message.
13 years, 9 months
2 questions
by Leandro Zipitria
Dear Gretl community,
If I am working with a restricted version of a variable (using smpl
--restrict), the mean, standard deviation, etc. reported is for the variable
as a whole or just the restricted sample? If its not is there any way of
calculating the mean of the restricted sample without actually downgrading
the database?
As a second answer, I am creating a doble loop for iterating mean and
standar deviation from a variable. I want to create a matix that store the
results of each calculation. That is, I have a panel, and want to restrict
it looping on one variable (city) which will be the columns, and the time
the rows. Each time gretl compute one statistic, I am trying to store it in
the matrix, following the previous order. Is this possible?
Regards,
Leandro
13 years, 9 months
Re: [Gretl-users] how to delete observations and merge databases
by Allin Cottrell
On Fri, 3 Jun 2011, Leandro Zipitria wrote:
> I have a panel dataset and I want to delete the first 31 observations of
> each unit. I have read that one possible way is to restrict the sample and
> then save it.
That's right.
genr time
smpl time > 31 --restrict
store smaller.gdt
> The second one is a little more tricky. I have one dataset as a panel, and
> another that has additional information of some of the variables, but just
> once. The two databases are of different length. Is there any way that gretl
> merge this two databases and repeat each value of ?
Yes. Given a panel dataset of dimension N x T you can append data
with a series length of N or T and the added data will be repeated
as appropriate to complete the panel.
Allin Cottrell
13 years, 10 months
