arima and info criteria
by Bob McCall
Greetings:
When calculating information criteria for arima models, Gretl seems to use k
+ 1 parameters
instead of k parameters.
Bob
13 years
bootstrapped skewness adjusted t test
by Md. Mohan Uddin
*Hi all..*
*
*
*Good day..*
*
*
*Is it possible to calculate bootstrapped skewness adjusted t test [**
suggested by Johnson (1978); also
**
proposed by Lyon, Barber, and Tsai (1999), 'Improved Methods for Tests
**
of Long-Run Abnormal Stock Returns', The Journal of Finance, Vol. 54,
**
No. 1, pp. 165-201
] for a skewed data in Gretl? If it is possible, how can I do this,
including the critical value estimation?
*
*
*
*Thank you in advance for the help.*
(এম মহান উদ্দিন)
Md. Mohan Uddin
PhD Candidate | College of Business | Universiti Utara Malaysia
Sintok, Kedah, Malaysia
____________________________________________________________________________
Assistant Professor (on study leave) | School of Business | United
International University
Dhaka, Bangladesh | www.uiu.ac.bd
13 years
Re: [Gretl-users] scatter plot with non-binary factor separation
by Allin Cottrell
On Fri, 29 Apr 2011, Ignacio Diaz-Emparanza wrote:
> El 28/04/11 19:36, Ferenci Tamas escribió:
> > Hello all,
> >
> > First of all: thank you Allin! It works perfectly, exactly that I was
> > thinking of. I can even edit the plot gretl-stlye after running the
> > script, very nice. (And I'm also a bit relieved that not I was missing
> > a GUI feature for this...) By the way, I really appreciate the way you
> > help everyone on this list, thank you again!
> >
> > Just out of curiosity: what is the rationale behind limiting the GUI
> > to binary variables? Enabling the usage of any discrete variable
> > would in no way alter the possibility of still using a binary variable
> > (it would be a fully "backward compatible" change, so to say), and it
> > also doesn't seem to be too complicated...
>
> I am using Allin's script as well, for a cross-section model and a
> discrete variable with three categories. I also vote for extending the
> "XY with factor separation" plot to allow for more categories, of course
> when our dear developers have time and are bored (no high priority).
OK, now in CVS and snapshots you can use any discrete variable,
not just a 0/1 dummy, with gnuplot and the --dummy option.
In the same line of business I've added a --factorized option for
the boxplot command, and enhanced the GUI boxplot options (e.g.,
on right-clicking a variable and selecting Boxplot).
Allin
13 years
Re: [Gretl-users] scatter plot with non-binary factor separation
by Allin Cottrell
On Mon, 2 May 2011, Ignacio Diaz-Emparanza wrote:
> El 29/04/11 20:37, Allin Cottrell escribió:
> >
> > OK, now in CVS and snapshots you can use any discrete variable,
> > not just a 0/1 dummy, with gnuplot and the --dummy option.
> >
> > In the same line of business I've added a --factorized option for
> > the boxplot command, and enhanced the GUI boxplot options (e.g.,
> > on right-clicking a variable and selecting Boxplot).
> >
> > Allin
>
> I have tried the new factorized plot, an I am obtaining this error:
>
> gnuplot PIB08 pob08 Cod_prov --dummy
> set xrange [1.797693135e+308:1.797693135e+308]
> ^
> "/home/ignacio/.gretl/gpttmp.XpUlk9", line 17: undefined value
I think this should now be fixed in CVS.
Allin
13 years
Re: [Gretl-users] how to define a variable
by Allin Cottrell
On Wed, 4 May 2011, Qi Shi wrote:
> There are three variables y,x.and z in my data, in which z is a
> dummy. I would like to define a new variable w: if z=1, w=y;
> otherwise w=-infinity. What is the scripts? thanks!
In principle,
w = (z==1)? y : -1/0
However, you can't actually represent infinities in gretl: the
expression "-1/0" will produce a missing value (NA).
Allin Cottrell
13 years
how to define a variable
by Qi Shi
hi
There are three variables y,x.and z in my data, in which z is a dummy. I would like to define a new variable w: if z=1, w=y; otherwise w=-infinity.
What is the scripts? thanks!
shi,qi
13 years
Re: [Gretl-users] New mailing list?
by MICHAEL BOLDIN
I was part of asking about making new mailing list but after reading
the replies and recalling my experiences running such a list at one
time, it is probably not worthwhile. If it becomes popular because
experienced GRETL users do respond we will surely encourage a lot of:
'do my econometrics homework for me' (as someone else points out) or
worse: 'how do I apply a technique for which I have no idea about how
it works but want to use it for my dissertation'. Many of the
remainder are likely to be naive and show the person asking the
questions did not bother to first look in their econometrics textbook
Most important: Anyone motivated to make it work (inside or outside
of the GRETL community) could easily start such a list independently
of GRETL. A Google
group is easy to set up. And if Allin, Sven, Jack and others involved
in development and enhancements to GRETL were to encourage something
linked to GRETL, the value added is unlikely to exceed the
distraction.
So I change my vote to letting things stand as they are-- everyone
seeing a few econometrics questions related to GREL every once in a
while.
However, I think an item in the GRETL Help menu for 'Check and use
the GRETL developers listserve' would be a worthwhile addition.
Instead of making it a direct 'Send question to listserve' I suggest
encouraging new users to search the listserve first by simply pointing
to http://lists.wfu.edu/mailman/listinfo/gretl-devel and adding the
ground rules to this page.
--my 2 cents
13 years
Stacking Database
by Iuri Queiroz
Hi, i'm from Brasil and recently discovered the GRETL in order to accomplish
my masters degree.
Unfortunetly, given the original data lenght and organization, the only way
i found to index and extract that to my database was in that manner:
State1
State2
State3
--
Iuri Queiroz
13 years
Re: [Gretl-users] a minor problem
by Allin Cottrell
On Tue, 3 May 2011, Qi Shi wrote:
> when i define a lagged variable of one variable, say "x", it hides in
> x, it does not exist in the regression panel. what can i do to fix
> it?
Use the "lags" button in the model specification window.
If you want a lag to show up as a variable in its own right,
define it manually, as in
lag1x = x(-1)
Allin Cottrell
13 years
a minor problem
by Qi Shi
hi
when i define a lagged variable of one variable, say "x", it hides in
x, it does not exist in the regression panel. what can i do to fix
it?
thanks!
--
shi, qi
13 years
