De: "gretl-users-request@lists.wfu.edu" <gretl-users-request@lists.wfu.edu>
Para: gretl-users@lists.wfu.edu
Enviado: Miércoles, 17 de agosto, 2011 11:00:03
Asunto: Gretl-users Digest, Vol 55,
Issue 15
Send Gretl-users mailing list submissions to
gretl-users@lists.wfu.eduTo subscribe or unsubscribe via the World Wide Web, visit
http://lists.wfu.edu/mailman/listinfo/gretl-usersor, via email, send a message with subject or body 'help' to
gretl-users-request@lists.wfu.eduYou can reach the person managing the list at
gretl-users-owner@lists.wfu.eduWhen replying, please edit your Subject line so it is more specific
than "Re: Contents of
Gretl-users digest..."
Today's Topics:
1. Re: EGARCH parameter estimation via "gig" GUI
(Riccardo (Jack) Lucchetti)
2. Re: New options for the script editor (Riccardo (Jack) Lucchetti)
3. Re: installing gretl in Ubuntu 11.04 (Riccardo (Jack) Lucchetti)
4. Re: Variance/covariance matrix via GARCH(1,1)
(Riccardo (Jack) Lucchetti)
----------------------------------------------------------------------
Message: 1
Date: Wed, 17 Aug 2011 15:43:24 +0200 (CEST)
From: "Riccardo (Jack) Lucchetti" <
r.lucchetti@univpm.it>
Subject: Re: [Gretl-users] EGARCH parameter estimation via "gig" GUI
To: Gretl list <
gretl-users@lists.wfu.edu>
Message-ID:
<
alpine.DEB.2.02.1108171539310.4497@ec-4.econ.univpm.it>
Content-Type: text/plain; charset="utf-8"
On Mon, 8 Aug 2011, Oscar Soppelsa wrote:
> I was wondering the following: in the Exponential GARCH(1,1) model
> there?s a parameter in addition to ?, ? and ?, and this is ?. gretl uses
> the EGARCH(p,q) formulation without ? [? multiplies the residuals in
> g(?t-1)]. If I need to make a forecast on t + n periods in the future, I
> would need the ? estimated value: does anyone know how may I get that
> value?
Hmm; the parametrisation gig uses is reported in the pdf doc file as
equation 9. I don't quite get what kind of parametrisation for the EGARCH
model you're referring to. Could you be more explicit, please? If you
don't feel
like writing the specification you have in mind for the
conditional variance, please provide a reference.
Riccardo (Jack) Lucchetti
Dipartimento di Economia
Universit? Politecnica delle Marche
r.lucchetti@univpm.ithttp://www.econ.univpm.it/lucchetti------------------------------
Message: 2
Date: Wed, 17 Aug 2011 15:50:51 +0200 (CEST)
From: "Riccardo (Jack) Lucchetti" <
r.lucchetti@univpm.it>
Subject: Re: [Gretl-users] New options for the script editor
To: Gretl list <
gretl-users@lists.wfu.edu>
Message-ID: <
alpine.DEB.2.02.1108171545330.4497@ec-4.econ.univpm.it>
Content-Type: text/plain; charset="iso-8859-15"
On Tue, 9 Aug 2011, amaryl wrote:
> On Mon, 2011-08-08 at 22:04 -0400, Allin Cottrell wrote:
>> On Tue, 2 Aug 2011, Summers, Peter wrote:
>>
>>>> Sometimes a tool to forcibly terminate a running script would come very
>>> handy, too. Maybe a combined "Start/Stop" button or something alike.
>>>
>>> I found myself looking for the "stop" button just yesterday ;-).
>>
>>> From a programmer's point of view, the question is: where should we
>> stick the handlers for aborting a script? Is everyone who's putting
>> forward this idea thinking in terms of breaking out of a gretl
loop?
>>
>> Notice that you have a "break" command for loops, so with some
>> foresight you can arrange a conditional breakout if things are not
>> going well.
>
> Personally, I am not thinking of breaking out of faulty loops.
> In one of my scripts I had a lot of time-consuming loops. When I wanted
> to check changes in my script not directly related to the loops, I
> usually commented them out, but occasionally I forgot. A stop-button
> would have been useful. "break" obviously doesn't help me in that case.
>
> In general, I think a stop-button is useful in cases where you notice
> that you have lacked foresight ;-)
The problem with a "break" button is that the program has to constantly
check if the button has been pressed and, if so, take the appropriate
action. This slows down execution and I personally don't like it very
much. This said, it
has happened to me to long for a break button, like
for example when you run some estimation command that is known to take
minutes and you realise just after having pressed "OK" that you forgot to
add a variable or so.
What we may want to do is think about some mechanism for interrupting the
current command in the GUI client, and advise users to use the unstoppable
might of the CLI client if performance is of paramount importance.
Thoughts?
Riccardo (Jack) Lucchetti
Dipartimento di Economia
Universit? Politecnica delle Marche
r.lucchetti@univpm.ithttp://www.econ.univpm.it/lucchetti------------------------------
Message: 3
Date: Wed, 17 Aug 2011 16:00:21 +0200 (CEST)
From: "Riccardo (Jack) Lucchetti" <
r.lucchetti@univpm.it>
Subject: Re: [Gretl-users] installing gretl in Ubuntu 11.04
To: Gretl list <
gretl-users@lists.wfu.edu>
Message-ID: <
alpine.DEB.2.02.1108171556140.4497@ec-4.econ.univpm.it>
Content-Type: text/plain; charset="iso-8859-15"
On Thu, 11 Aug 2011, Neil Hepburn wrote:
> Greetings I am trying to install Gretl 1.9.5 in Ubuntu 11.04 as per the
> note on the Sourceforge site about using the Debian version instead of
> the Ubuntu version. ?Can someone tell me the repository to use in my
> /etc/apt/sources.list file?
ftp://ftp.debian.org testing main
should do the trick, I guess. However, IMHO Linux users are almost
always better off building from source. I have no direct experience with
ubuntu 11.04, but I believe there shouldn't be any problem.
Riccardo (Jack) Lucchetti
Dipartimento di Economia
Universit? Politecnica delle Marche
r.lucchetti@univpm.ithttp://www.econ.univpm.it/lucchetti------------------------------
Message: 4
Date: Wed, 17 Aug 2011 16:03:03 +0200 (CEST)
From: "Riccardo (Jack) Lucchetti" <
r.lucchetti@univpm.it>
Subject: Re: [Gretl-users] Variance/covariance matrix via GARCH(1,1)
To: Gretl list <
gretl-users@lists.wfu.edu>
Message-ID: <
alpine.DEB.2.02.1108171601190.4497@ec-4.econ.univpm.it>
Content-Type: text/plain; charset="iso-8859-15"
On Thu, 11 Aug 2011, Oscar Soppelsa wrote:
> May you tell me how may I estimate a variance/covariance matrix using
> GARCH(1,1) model?
I'm afraid I don't understand what you want to do. Do you need the
covariance matrix of the estimated parameters or a multivariate garch
model (or something else altogether)?
Riccardo (Jack) Lucchetti
Dipartimento di Economia
Universit? Politecnica delle Marche
r.lucchetti@univpm.ithttp://www.econ.univpm.it/lucchetti------------------------------
_______________________________________________
Gretl-users mailing list
Gretl-users@lists.wfu.eduhttp://lists.wfu.edu/mailman/listinfo/gretl-usersEnd of Gretl-users Digest, Vol 55, Issue 15
*******************************************