Re: [Gretl-users] re-organizing panel data
by Allin Cottrell
On Wed, 13 Apr 2011, artur bala wrote:
> I have a 5 x 12 panel data that I processed, by mistake, as a 6 x 10 panel.
> Well, I tried to re-organize the panel structure but if I go through the
> "stacked time series" option no change takes place. Instead, if I select
> the "stacked cross section" everything works fine.
Thanks for the report. That's now fixed in CVS. Just for the
record, that was a GUI-specific problem: the setobs command would
correctly adjust the n and T values for the panel in this case.
Allin Cottrell
15 years
Re: [Gretl-users] Problems with language preference
by Allin Cottrell
On Thu, 14 Apr 2011, [ISO-8859-1] Carlos Henrique Coêlho de Andrade wrote:
> Em 14/04/2011, às 10:38, Allin Cottrell <cottrell(a)wfu.edu> escreveu:
> > Can you give an example of how a non-Portuguese speaker can
> > recognize which Portuguese variant is being used? If I know how to
> > tell the difference I can try testing on OS X.
>
> Loiking at the main menu:
>
> File -> Ficheiro (Portugal) or Arquivo (Brasil).
Thanks, I'll take a look at that tonight.
Allin Cottrell
15 years
Re: [Gretl-users] Problems with language preference
by Allin Cottrell
On Thu, 14 Apr 2011, Henrique Andrade wrote:
> I've installed the latest Gretl snapshot (Mac version) and
> Gretl stopped to use Brazilian Portuguese. The interesting
> fact is that I had made no changes in the Gretl preferences.
>
> Now, even if I choose the option "Automatic" or "Portuguese
> (Brazilian)" Gretl uses the Portuguese (from Portugal).
Can you give an example of how a non-Portuguese speaker can
recognize which Portuguese variant is being used? If I know how to
tell the difference I can try testing on OS X.
Allin Cottrell
15 years
how to activate x-12-arima?
by Qi Shi
Hi
i have installed x-12-arima for Windows, but the button is still not
activated. why?
best,
--
shi, qi
15 years
Problems with language preference
by Henrique Andrade
Dear Gretl Community,
I've installed the latest Gretl snapshot (Mac version) and
Gretl stopped to use Brazilian Portuguese. The interesting
fact is that I had made no changes in the Gretl preferences.
Now, even if I choose the option "Automatic" or "Portuguese
(Brazilian)" Gretl uses the Portuguese (from Portugal).
Is anyone experiencing this behavior?
Best,
--
*Henrique C. de Andrade*
Doutorando em Economia Aplicada
Universidade Federal do Rio Grande do Sul
www.ufrgs.br/ppge
15 years
Re: [Gretl-users] GMM Instruments Lagged Independent Variables
by Allin Cottrell
On Wed, 13 Apr 2011, Dempsey, Keely wrote:
> I am trying to estimate GMM using lagged (-1) values of the two
> independent variables in my equation as instruments. When I try
> to estimate an error message saying "missing values" appears.
> Does anyone know how to correct this?
You need to (a) fill in the holes in your data set, or (b) choose
a smaller sample that contains no missing values after defining
the lags.
Allin Cottrell
15 years
panel plot
by artur bala
Dear Allin,
It seems like in the "panel plot" window, both options on boxplot do
produce the same graph.
Best,
artur
--
Artur BALA
development economist, consultant
phone: +216 22 99 73 44
skype: artur.bala.tn
email: artur.bala.tn(a)gmail.com
*********************************
15 years
re-organizing panel data
by artur bala
Dear Allin,
I have a 5 x 12 panel data that I processed, by mistake, as a 6 x 10 panel.
Well, I tried to re-organize the panel structure but if I go through the
"stacked time series" option no change takes place. Instead, if I select
the "stacked cross section" everything works fine.
regards,
artur
--
Artur BALA
development economist, consultant
phone: +216 22 99 73 44
skype: artur.bala.tn
email: artur.bala.tn(a)gmail.com
*********************************
15 years
Re: [Gretl-users] test for autocorrelation in panel estimation
by Allin Cottrell
On Tue, 12 Apr 2011, Hakim, Sam wrote:
> I am estimating demand elasticities using panel data and I am
> using effect model in Gretl. I suspect that the independent and
> dependent variables are correlated due to a simulataneous
> equation bias.
>
> Is there a simple test for autocorrelation I can run? For
> whatever reason, the DW test option is not available for this
> model.
Testing for autocorrelation doesn't tell you anything about
simultaneous equations bias.
But if the DW test is not reported that suggests that either the
time-series length is too short or there are missing values within
the sample. If the problem is missing values and you're willing to
ignore that issue, you could save the residuals (they're available
as $uhat) and construct a test (Durbin-Watson or otherwise)
manually -- e.g. by setting the missing residuals to zero.
Allin Cottrell
15 years
GMM Instruments Lagged Independent Variables
by Dempsey, Keely
Hello,
I am trying to estimate GMM using lagged (-1) values of the two independent variables in my equation as instruments. When I try to estimate an error message saying "missing values" appears. Does anyone know how to correct this?
Thank you
.
15 years
