Stefano Fachin | 24 Jul 19:50 2016
Picon

CDF underflow

My guess is that zero, although approximate, is the most meaningful 
answer - perhaps supplemented with a cautionary note.
thanks!
Stefano
Stefano Fachin | 22 Jul 15:14 2016
Picon

pvalue

dear all,
I run into an unexpected behaviour of the "pvalue" utility, which crashes if required to compute the pvalue of a very small number using a Chi square with a large number of degrees of freedom. For instance, setting 227 degrees of freedom the pvalue is computed only for numbers larger than about 0.165. For lower values the reply is "impossible to compute the pvalue" in the GUI and "NA" in a batch script (v. 2016b, 2016-04-14) Of course, nobody in his right mind will knowingly want to compute such a pvalue, but when running in a script it may happen and the NA output does not look good.
thanks!
Stefano


--
____________________________________________________________________
Stefano Fachin Professore Ordinario di Statistica Economica Dip. di Scienze Statistiche Università di Roma "La Sapienza" P.le A. Moro 5 - 00185 Roma - Italia Tel. +39-06-49910834 fax +39-06-49910072 web http://stefanofachin.site.uniroma1.it/
<div><div dir="ltr">
<div>
<div>
<div>dear all,<br>
</div>I run into an unexpected behaviour of the "pvalue" utility, which crashes if required to compute the pvalue of a very small number using a Chi square with a large number of degrees of freedom. For instance, setting 227 degrees of freedom the pvalue is computed only for numbers larger than about 0.165. For lower values the reply is "impossible to compute the pvalue" in the GUI and "NA" in a batch script (v. 2016b, 2016-04-14) Of course, nobody in his right mind will knowingly want to compute such a pvalue, but when running in a script it may happen and the NA output does not look good.<br>
</div>thanks!<br>
</div>Stefano<br><div><div>
<br clear="all"><div><div><div>
<br>-- <br><div class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div><div dir="ltr">____________________________________________________________________<br>Stefano Fachin
Professore Ordinario di Statistica Economica
Dip. di Scienze Statistiche
Universit&agrave; di Roma "La Sapienza"
P.le A. Moro 5 - 00185 Roma - Italia
Tel. +39-06-49910834
fax  +39-06-49910072
web <a href="http://stefanofachin.site.uniroma1.it/" target="_blank">http://stefanofachin.site.uniroma1.it/</a><a href="http://w3.uniroma1.it/fachin/" target="_blank"></a>
</div></div></div></div>
</div></div></div>
</div></div>
</div></div>
George Matysiak | 21 Jul 00:12 2016
Picon

Re: Gretl-users Digest, Vol 114, Issue 9

Alin,

Thanks for that. Option 1 works apart from Hansl Primer - still picks the old A4 version up.


Contact number +48 781 415 432

"In God we trust, all others bring data."

On 20 July 2016 at 19:21, <gretl-users-request-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org> wrote:
Send Gretl-users mailing list submissions to
        gretl-users-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org

To subscribe or unsubscribe via the World Wide Web, visit
        http://lists.wfu.edu/mailman/listinfo/gretl-users
or, via email, send a message with subject or body 'help' to
        gretl-users-request-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org

You can reach the person managing the list at
        gretl-users-owner-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org

When replying, please edit your Subject line so it is more specific
than "Re: Contents of Gretl-users digest..."


Today's Topics:

   1. Re: Gretl-users Digest, Vol 114, Issue 8 (George Matysiak)
   2. Re: Gretl-users Digest, Vol 114, Issue 8 (Sven Schreiber)
   3. Re: Gretl-users Digest, Vol 114, Issue 8 (Allin Cottrell)


----------------------------------------------------------------------

Message: 1
Date: Wed, 20 Jul 2016 17:50:03 +0100
From: George Matysiak <gmatysiak <at> gmail.com>
To: gretl-users-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org
Subject: Re: [Gretl-users] Gretl-users Digest, Vol 114, Issue 8
Message-ID:
        <CAEWMk7u1z-=vs59fMUnnP0kiuTmzhcXoauxXja6oMKtgHqRQ=w <at> mail.gmail.com>
Content-Type: text/plain; charset="utf-8"

Sven, thanks for the reply. Your suggestions do not work - I still get the
March 2016 files.




*Contact number +48 781 415 432**"In God we trust, all others bring data."*

On 20 July 2016 at 17:00, <gretl-users-request-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org> wrote:

> Send Gretl-users mailing list submissions to
>         gretl-users-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org
>
> To subscribe or unsubscribe via the World Wide Web, visit
>         http://lists.wfu.edu/mailman/listinfo/gretl-users
> or, via email, send a message with subject or body 'help' to
>         gretl-users-request-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org
>
> You can reach the person managing the list at
>         gretl-users-owner-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org
>
> When replying, please edit your Subject line so it is more specific
> than "Re: Contents of Gretl-users digest..."
>
>
> Today's Topics:
>
>    1. Re: User Guide Versionand other documentation and Gretl 2016c
>       (Sven Schreiber)
>    2. Re: F-test: Fixed Effects vs Pooled OLS (Sven Schreiber)
>    3. Re: F-test: Fixed Effects vs Pooled OLS (Bruno Gobeil)
>
>
> ----------------------------------------------------------------------
>
> Message: 1
> Date: Wed, 20 Jul 2016 16:27:05 +0200
> From: Sven Schreiber <svetosch <at> gmx.net>
> To: gretl-users-npDYnXcwJHmHXe+LvDLADg@public.gmane.org.edu
> Subject: Re: [Gretl-users] User Guide Versionand other documentation
>         and Gretl 2016c
> Message-ID: <f581fb81-6b98-a1ea-2ea7-16167705c9ac-hi6Y0CQ0nG0@public.gmane.org>
> Content-Type: text/plain; charset=windows-1252; format=flowed
>
> Am 16.07.2016 um 23:41 schrieb George Matysiak:
> > Having installed Gretl 2016c I notice that the User Guide is dated March
> > 2016, as is the Command Reference, Hansl Primer and Package Function
> > Guide. Are the latest versions not automatically installed on a Gretl
> > upodate? Thanks.
> >
>
> Sorry for the non-response, apparently it's vacation time. I presume
> you're using Windows. If you uninstall the old gretl version first, then
> it should be the latest pdf versions. If you're as lazy as I am and
> simply install the new version over the old one then not necessarily.
> You could manually delete the pdfs and then gretl will (try to) download
> the current versions when you select the corresponding menu items.
>
> cheers,
> sven
>
>
> ------------------------------
>
> Message: 2
> Date: Wed, 20 Jul 2016 16:35:33 +0200
> From: Sven Schreiber <svetosch <at> gmx.net>
> To: gretl-users-npDYnXcwJHmHXe+LvDLADg@public.gmane.org.edu
> Subject: Re: [Gretl-users] F-test: Fixed Effects vs Pooled OLS
> Message-ID: <4ce96501-77fa-eb0b-ce9c-da970cd4a2d0-hi6Y0CQ0nG0@public.gmane.org>
> Content-Type: text/plain; charset=windows-1252; format=flowed
>
> Am 20.07.2016 um 15:28 schrieb Bruno Gobeil:
> > Hello!
> >
> >
> >
> > I would like to better understand the rational for using the following
> > formula for determining the denominator degrees of freedom for the
> > F-test: n(t-1)-(k-1); where n is the number of regions, t the number of
> > years, k the number of parameters, including the constant. I thought
> > that the use of the de-meaned data approach compared to LSDV approach
> > for the fixed effects model would lead to a higher number of denominator
> > degrees of freedom, as suggested in the Gretl Guide, with the following
> > formula: nt-k.
> >
>
> If I understand your question correctly, then here is my answer: LSDV
> and de-meaned data fixed effects ("within" estimation) are equivalent
> for testing purposes. To put it differently, de-meaning is also a
> statistical estimation procedure, because you do not know the expected
> population values a priori and hence you have to estimate them via the
> arithmetic means. Hence you cannot gain d.o.f. by the within/de-meaned
> estimator.
>
> This is not gretl-specific, of course.
>
> hth,
> sven
>
>
> ------------------------------
>
> Message: 3
> Date: Wed, 20 Jul 2016 14:41:00 +0000
> From: Bruno Gobeil <bruno.gobeil-rcFuL2VrcYPQT0dZR+AlfA@public.gmane.org>
> To: Gretl list <gretl-users-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org>
> Subject: Re: [Gretl-users] F-test: Fixed Effects vs Pooled OLS
> Message-ID:
>         <
> BLUPR0401MB1713A32523F2BE9B4BE69955EB080 <at> BLUPR0401MB1713.namprd04.prod.outlook.com
> >
>
> Content-Type: text/plain; charset="iso-8859-1"
>
> Thanks very much for your quick response. It is much appreciated.
>
> Regards,
>
> Bruno Gobeil
> Senior Consultant | Consultant principal
> DUNSKY ENERGY CONSULTING | DUNSKY EXPERTISE EN ?NERGIE
> [t] 514.504.9030??*26?? [f] 514.289.2665?? [e] bruno.gobeil-rcFuL2VrcYPQT0dZR+AlfA@public.gmane.org
>
>
>
> NOTICE: This message (including any attachments) is intended for the sole
> use of the individual or entity to which it is addressed, and contains
> information that is privileged, confidential and exempt from disclosure.
> ?Barring explicit indication to the contrary in the text of the message,
> any copying, distribution or dissemination of any part of this email
> (including any attachments), by the intended or accidental recipient, is
> strictly prohibited. If you have received this communication in error,
> please notify us immediately. ?Thank You.?
>
> AVIS?: Ce message (et les pi?ces qui y sont jointes) est destin? ? l'usage
> exclusif de la personne ou de l'entit? ? laquelle il est adress?, et
> renferme des renseignements privil?gi?s et confidentiels qui ne doivent pas
> ?tre divulgu?s. Sauf si le message invite explicitement au contraire, il
> est strictement interdit de copier, distribuer ou diffuser cette
> communication (et les pi?ces qui y sont jointes), en tout ou en partie,
> cette interdiction s'appliquant tant au r?cipiendaire voulu
> qu'involontaire.? Si vous avez re?u cette communication par erreur,
> veuillez nous en aviser imm?diatement. ?Merci.?
>
> -----Original Message-----
> From: gretl-users-bounces-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org [mailto:
> gretl-users-bounces-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org] On Behalf Of Sven Schreiber
> Sent: July 20, 2016 10:36 AM
> To: gretl-users-npDYnXcwJHmHXe+LvDLADg@public.gmane.org.edu
> Subject: Re: [Gretl-users] F-test: Fixed Effects vs Pooled OLS
>
> Am 20.07.2016 um 15:28 schrieb Bruno Gobeil:
> > Hello!
> >
> >
> >
> > I would like to better understand the rational for using the following
> > formula for determining the denominator degrees of freedom for the
> > F-test: n(t-1)-(k-1); where n is the number of regions, t the number
> > of years, k the number of parameters, including the constant. I
> > thought that the use of the de-meaned data approach compared to LSDV
> > approach for the fixed effects model would lead to a higher number of
> > denominator degrees of freedom, as suggested in the Gretl Guide, with
> > the following
> > formula: nt-k.
> >
>
> If I understand your question correctly, then here is my answer: LSDV and
> de-meaned data fixed effects ("within" estimation) are equivalent for
> testing purposes. To put it differently, de-meaning is also a statistical
> estimation procedure, because you do not know the expected population
> values a priori and hence you have to estimate them via the arithmetic
> means. Hence you cannot gain d.o.f. by the within/de-meaned estimator.
>
> This is not gretl-specific, of course.
>
> hth,
> sven
> _______________________________________________
> Gretl-users mailing list
> Gretl-users-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org
> http://lists.wfu.edu/mailman/listinfo/gretl-users
>
>
>
> ------------------------------
>
> _______________________________________________
> Gretl-users mailing list
> Gretl-users-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org
> http://lists.wfu.edu/mailman/listinfo/gretl-users
>
> End of Gretl-users Digest, Vol 114, Issue 8
> *******************************************
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.wfu.edu/pipermail/gretl-users/attachments/20160720/6a541a0b/attachment-0001.html>

------------------------------

Message: 2
Date: Wed, 20 Jul 2016 19:55:13 +0200
From: Sven Schreiber <svetosch <at> gmx.net>
To: gretl-users-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org
Subject: Re: [Gretl-users] Gretl-users Digest, Vol 114, Issue 8
Message-ID: <bfdce3ac-706f-9d47-9dce-55c3c180622b-hi6Y0CQ0nG0@public.gmane.org>
Content-Type: text/plain; charset=windows-1252; format=flowed

Am 20.07.2016 um 18:50 schrieb George Matysiak:
> Sven, thanks for the reply. Your suggestions do not work - I still get
> the March 2016 files.
>

Well if you really deleted the old files manually it sounds very
improbable to me that gretl would download them again. So I guess the
old files must still be lying around on your hard disk somewhere where
gretl is looking for them. Unfortunately right now I'm not sure exactly
what those locations could be.

In any case, if you need to look at the new files they are also here:
https://sourceforge.net/projects/gretl/files/manual/

cheers,
sven



------------------------------

Message: 3
Date: Wed, 20 Jul 2016 14:21:45 -0400 (EDT)
From: Allin Cottrell <cottrell <at> wfu.edu>
To: Gretl list <gretl-users <at> lists.wfu.edu>
Subject: Re: [Gretl-users] Gretl-users Digest, Vol 114, Issue 8
Message-ID: <alpine.LFD.2.20.3.1607201404530.2507-0km7b9lZrJwlRp7syxWybdHuzzzSOjJt@public.gmane.org>
Content-Type: text/plain; charset=US-ASCII; format=flowed

On Wed, 20 Jul 2016, George Matysiak wrote:

> Sven, thanks for the reply. Your suggestions do not work - I still
> get the March 2016 files.

Ah, I think I know what may be happening here. Have you at some
point selected A4-format documentation? (Under
/Tools/Preferences/General there's an item "PDF manual preference"
where you can select US letter paper or A4 paper.)

Here's the thing: each release package includes current versions of
the Gretl User's Guide and the Gretl Command Reference (PDF files)
in US letter format. But if you want the A4 versions they are
downloaded on demand. And in this respect there's a gap in our
updating logic: if you have once downloaded (for example) the A4
User's Guide, then it will be found on your system thereafter and
will not be downloaded again, even if it goes out of date.
Uninstalling gretl won't help: the old A4 PDF files will not get
deleted since they were not part of the initial gretl installation.

We need to figure out a proper fix for this, but in the meantime
here are two possible work-arounds:

1. Select US letter format under Preferences, and you'll see the new
PDF files that were installed with gretl 2016c.

2. Manually delete the old PDF files under the "doc" folder in your
gretl installation. Then when you go to consult them the new
versions will get downloaded from sourceforge.

On the other hand, if the Preferences/General dialog is NOT showing
A4 as your preferred PDF format, then I don't know what's happening.
I have verified that the 2016c release files on sourceforge contain
the Guide and Reference as of July 6, 2016.

Allin Cottrell


------------------------------

_______________________________________________
Gretl-users mailing list
Gretl-users-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org
http://lists.wfu.edu/mailman/listinfo/gretl-users

End of Gretl-users Digest, Vol 114, Issue 9
*******************************************

<div>
<div dir="ltr">
<div class="gmail_default">Alin,<br><br>
</div>
<div class="gmail_default">Thanks for that. Option 1 works apart from Hansl Primer - still picks the old A4 version up.<br>
</div>
</div>
<div class="gmail_extra">
<br clear="all"><div><div class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr">
<div><br></div>
<span>Contact number +48 781 415 432<br><br></span>"In God we trust, all others bring data."</div></div></div></div></div></div></div></div></div></div></div></div></div>
<br><div class="gmail_quote">On 20 July 2016 at 19:21,  <span dir="ltr">&lt;<a href="mailto:gretl-users-request@..." target="_blank">gretl-users-request@...</a>&gt;</span> wrote:<br><blockquote class="gmail_quote">Send Gretl-users mailing list submissions to<br>
&nbsp; &nbsp; &nbsp; &nbsp; <a href="mailto:gretl-users@...">gretl-users@...</a><br><br>
To subscribe or unsubscribe via the World Wide Web, visit<br>
&nbsp; &nbsp; &nbsp; &nbsp; <a href="http://lists.wfu.edu/mailman/listinfo/gretl-users" rel="noreferrer" target="_blank">http://lists.wfu.edu/mailman/listinfo/gretl-users</a><br>
or, via email, send a message with subject or body 'help' to<br>
&nbsp; &nbsp; &nbsp; &nbsp; <a href="mailto:gretl-users-request@....edu">gretl-users-request@...</a><br><br>
You can reach the person managing the list at<br>
&nbsp; &nbsp; &nbsp; &nbsp; <a href="mailto:gretl-users-owner@...du">gretl-users-owner@...</a><br><br>
When replying, please edit your Subject line so it is more specific<br>
than "Re: Contents of Gretl-users digest..."<br><br><br>
Today's Topics:<br><br>
&nbsp; &nbsp;1. Re: Gretl-users Digest, Vol 114, Issue 8 (George Matysiak)<br>
&nbsp; &nbsp;2. Re: Gretl-users Digest, Vol 114, Issue 8 (Sven Schreiber)<br>
&nbsp; &nbsp;3. Re: Gretl-users Digest, Vol 114, Issue 8 (Allin Cottrell)<br><br><br>
----------------------------------------------------------------------<br><br>
Message: 1<br>
Date: Wed, 20 Jul 2016 17:50:03 +0100<br>
From: George Matysiak &lt;<a href="mailto:gmatysiak@...">gmatysiak <at> gmail.com</a>&gt;<br>
To: <a href="mailto:gretl-users@...">gretl-users@...</a><br>
Subject: Re: [Gretl-users] Gretl-users Digest, Vol 114, Issue 8<br>
Message-ID:<br>
&nbsp; &nbsp; &nbsp; &nbsp; &lt;CAEWMk7u1z-=vs59fMUnnP0kiuTmzhcXoauxXja6oMKtgHqRQ=<a href="mailto:w <at> mail.gmail.com">w <at> mail.gmail.com</a>&gt;<br>
Content-Type: text/plain; charset="utf-8"<br><br>
Sven, thanks for the reply. Your suggestions do not work - I still get the<br>
March 2016 files.<br><br><br><br><br>
*Contact number <a href="tel:%2B48%20781%20415%20432" value="+48781415432">+48 781 415 432</a>**"In God we trust, all others bring data."*<br><br>
On 20 July 2016 at 17:00, &lt;<a href="mailto:gretl-users-request <at> lists.wfu.edu">gretl-users-request@...</a>&gt; wrote:<br><br>
&gt; Send Gretl-users mailing list submissions to<br>
&gt;&nbsp; &nbsp; &nbsp; &nbsp; &nbsp;<a href="mailto:gretl-users <at> lists.wfu.edu">gretl-users@...</a><br>
&gt;<br>
&gt; To subscribe or unsubscribe via the World Wide Web, visit<br>
&gt;&nbsp; &nbsp; &nbsp; &nbsp; &nbsp;<a href="http://lists.wfu.edu/mailman/listinfo/gretl-users" rel="noreferrer" target="_blank">http://lists.wfu.edu/mailman/listinfo/gretl-users</a><br>
&gt; or, via email, send a message with subject or body 'help' to<br>
&gt;&nbsp; &nbsp; &nbsp; &nbsp; &nbsp;<a href="mailto:gretl-users-request <at> lists.wfu.edu">gretl-users-request@...</a><br>
&gt;<br>
&gt; You can reach the person managing the list at<br>
&gt;&nbsp; &nbsp; &nbsp; &nbsp; &nbsp;<a href="mailto:gretl-users-owner <at> lists.wfu.edu">gretl-users-owner@...</a><br>
&gt;<br>
&gt; When replying, please edit your Subject line so it is more specific<br>
&gt; than "Re: Contents of Gretl-users digest..."<br>
&gt;<br>
&gt;<br>
&gt; Today's Topics:<br>
&gt;<br>
&gt;&nbsp; &nbsp; 1. Re: User Guide Versionand other documentation and Gretl 2016c<br>
&gt;&nbsp; &nbsp; &nbsp; &nbsp;(Sven Schreiber)<br>
&gt;&nbsp; &nbsp; 2. Re: F-test: Fixed Effects vs Pooled OLS (Sven Schreiber)<br>
&gt;&nbsp; &nbsp; 3. Re: F-test: Fixed Effects vs Pooled OLS (Bruno Gobeil)<br>
&gt;<br>
&gt;<br>
&gt; ----------------------------------------------------------------------<br>
&gt;<br>
&gt; Message: 1<br>
&gt; Date: Wed, 20 Jul 2016 16:27:05 +0200<br>
&gt; From: Sven Schreiber &lt;<a href="mailto:svetosch@...">svetosch <at> gmx.net</a>&gt;<br>
&gt; To: <a href="mailto:gretl-users@...">gretl-users@....edu</a><br>
&gt; Subject: Re: [Gretl-users] User Guide Versionand other documentation<br>
&gt;&nbsp; &nbsp; &nbsp; &nbsp; &nbsp;and Gretl 2016c<br>
&gt; Message-ID: &lt;<a href="mailto:f581fb81-6b98-a1ea-2ea7-16167705c9ac <at> gmx.net">f581fb81-6b98-a1ea-2ea7-16167705c9ac@...</a>&gt;<br>
&gt; Content-Type: text/plain; charset=windows-1252; format=flowed<br>
&gt;<br>
&gt; Am 16.07.2016 um 23:41 schrieb George Matysiak:<br>
&gt; &gt; Having installed Gretl 2016c I notice that the User Guide is dated March<br>
&gt; &gt; 2016, as is the Command Reference, Hansl Primer and Package Function<br>
&gt; &gt; Guide. Are the latest versions not automatically installed on a Gretl<br>
&gt; &gt; upodate? Thanks.<br>
&gt; &gt;<br>
&gt;<br>
&gt; Sorry for the non-response, apparently it's vacation time. I presume<br>
&gt; you're using Windows. If you uninstall the old gretl version first, then<br>
&gt; it should be the latest pdf versions. If you're as lazy as I am and<br>
&gt; simply install the new version over the old one then not necessarily.<br>
&gt; You could manually delete the pdfs and then gretl will (try to) download<br>
&gt; the current versions when you select the corresponding menu items.<br>
&gt;<br>
&gt; cheers,<br>
&gt; sven<br>
&gt;<br>
&gt;<br>
&gt; ------------------------------<br>
&gt;<br>
&gt; Message: 2<br>
&gt; Date: Wed, 20 Jul 2016 16:35:33 +0200<br>
&gt; From: Sven Schreiber &lt;<a href="mailto:svetosch@...">svetosch <at> gmx.net</a>&gt;<br>
&gt; To: <a href="mailto:gretl-users@...">gretl-users@....edu</a><br>
&gt; Subject: Re: [Gretl-users] F-test: Fixed Effects vs Pooled OLS<br>
&gt; Message-ID: &lt;<a href="mailto:4ce96501-77fa-eb0b-ce9c-da970cd4a2d0 <at> gmx.net">4ce96501-77fa-eb0b-ce9c-da970cd4a2d0@...</a>&gt;<br>
&gt; Content-Type: text/plain; charset=windows-1252; format=flowed<br>
&gt;<br>
&gt; Am 20.07.2016 um 15:28 schrieb Bruno Gobeil:<br>
&gt; &gt; Hello!<br>
&gt; &gt;<br>
&gt; &gt;<br>
&gt; &gt;<br>
&gt; &gt; I would like to better understand the rational for using the following<br>
&gt; &gt; formula for determining the denominator degrees of freedom for the<br>
&gt; &gt; F-test: n(t-1)-(k-1); where n is the number of regions, t the number of<br>
&gt; &gt; years, k the number of parameters, including the constant. I thought<br>
&gt; &gt; that the use of the de-meaned data approach compared to LSDV approach<br>
&gt; &gt; for the fixed effects model would lead to a higher number of denominator<br>
&gt; &gt; degrees of freedom, as suggested in the Gretl Guide, with the following<br>
&gt; &gt; formula: nt-k.<br>
&gt; &gt;<br>
&gt;<br>
&gt; If I understand your question correctly, then here is my answer: LSDV<br>
&gt; and de-meaned data fixed effects ("within" estimation) are equivalent<br>
&gt; for testing purposes. To put it differently, de-meaning is also a<br>
&gt; statistical estimation procedure, because you do not know the expected<br>
&gt; population values a priori and hence you have to estimate them via the<br>
&gt; arithmetic means. Hence you cannot gain d.o.f. by the within/de-meaned<br>
&gt; estimator.<br>
&gt;<br>
&gt; This is not gretl-specific, of course.<br>
&gt;<br>
&gt; hth,<br>
&gt; sven<br>
&gt;<br>
&gt;<br>
&gt; ------------------------------<br>
&gt;<br>
&gt; Message: 3<br>
&gt; Date: Wed, 20 Jul 2016 14:41:00 +0000<br>
&gt; From: Bruno Gobeil &lt;<a href="mailto:bruno.gobeil@...">bruno.gobeil@...</a>&gt;<br>
&gt; To: Gretl list &lt;<a href="mailto:gretl-users@...">gretl-users@...</a>&gt;<br>
&gt; Subject: Re: [Gretl-users] F-test: Fixed Effects vs Pooled OLS<br>
&gt; Message-ID:<br>
&gt;&nbsp; &nbsp; &nbsp; &nbsp; &nbsp;&lt;<br>
&gt; <a href="mailto:BLUPR0401MB1713A32523F2BE9B4BE69955EB080 <at> BLUPR0401MB1713.namprd04.prod.outlook.com">BLUPR0401MB1713A32523F2BE9B4BE69955EB080 <at> BLUPR0401MB1713.namprd04.prod.outlook.com</a><br>
&gt; &gt;<br>
&gt;<br>
&gt; Content-Type: text/plain; charset="iso-8859-1"<br>
&gt;<br>
&gt; Thanks very much for your quick response. It is much appreciated.<br>
&gt;<br>
&gt; Regards,<br>
&gt;<br>
&gt; Bruno Gobeil<br>
&gt; Senior Consultant | Consultant principal<br>
&gt; DUNSKY ENERGY CONSULTING | DUNSKY EXPERTISE EN ?NERGIE<br>
&gt; [t] 514.504.9030??*26?? [f] 514.289.2665?? [e] <a href="mailto:bruno.gobeil@...">bruno.gobeil@...</a><br>
&gt;<br>
&gt;<br>
&gt;<br>
&gt; NOTICE: This message (including any attachments) is intended for the sole<br>
&gt; use of the individual or entity to which it is addressed, and contains<br>
&gt; information that is privileged, confidential and exempt from disclosure.<br>
&gt; ?Barring explicit indication to the contrary in the text of the message,<br>
&gt; any copying, distribution or dissemination of any part of this email<br>
&gt; (including any attachments), by the intended or accidental recipient, is<br>
&gt; strictly prohibited. If you have received this communication in error,<br>
&gt; please notify us immediately. ?Thank You.?<br>
&gt;<br>
&gt; AVIS?: Ce message (et les pi?ces qui y sont jointes) est destin? ? l'usage<br>
&gt; exclusif de la personne ou de l'entit? ? laquelle il est adress?, et<br>
&gt; renferme des renseignements privil?gi?s et confidentiels qui ne doivent pas<br>
&gt; ?tre divulgu?s. Sauf si le message invite explicitement au contraire, il<br>
&gt; est strictement interdit de copier, distribuer ou diffuser cette<br>
&gt; communication (et les pi?ces qui y sont jointes), en tout ou en partie,<br>
&gt; cette interdiction s'appliquant tant au r?cipiendaire voulu<br>
&gt; qu'involontaire.? Si vous avez re?u cette communication par erreur,<br>
&gt; veuillez nous en aviser imm?diatement. ?Merci.?<br>
&gt;<br>
&gt; -----Original Message-----<br>
&gt; From: <a href="mailto:gretl-users-bounces@...">gretl-users-bounces@...</a> [mailto:<br>
&gt; <a href="mailto:gretl-users-bounces@...">gretl-users-bounces@...</a>] On Behalf Of Sven Schreiber<br>
&gt; Sent: July 20, 2016 10:36 AM<br>
&gt; To: <a href="mailto:gretl-users@...">gretl-users@....edu</a><br>
&gt; Subject: Re: [Gretl-users] F-test: Fixed Effects vs Pooled OLS<br>
&gt;<br>
&gt; Am 20.07.2016 um 15:28 schrieb Bruno Gobeil:<br>
&gt; &gt; Hello!<br>
&gt; &gt;<br>
&gt; &gt;<br>
&gt; &gt;<br>
&gt; &gt; I would like to better understand the rational for using the following<br>
&gt; &gt; formula for determining the denominator degrees of freedom for the<br>
&gt; &gt; F-test: n(t-1)-(k-1); where n is the number of regions, t the number<br>
&gt; &gt; of years, k the number of parameters, including the constant. I<br>
&gt; &gt; thought that the use of the de-meaned data approach compared to LSDV<br>
&gt; &gt; approach for the fixed effects model would lead to a higher number of<br>
&gt; &gt; denominator degrees of freedom, as suggested in the Gretl Guide, with<br>
&gt; &gt; the following<br>
&gt; &gt; formula: nt-k.<br>
&gt; &gt;<br>
&gt;<br>
&gt; If I understand your question correctly, then here is my answer: LSDV and<br>
&gt; de-meaned data fixed effects ("within" estimation) are equivalent for<br>
&gt; testing purposes. To put it differently, de-meaning is also a statistical<br>
&gt; estimation procedure, because you do not know the expected population<br>
&gt; values a priori and hence you have to estimate them via the arithmetic<br>
&gt; means. Hence you cannot gain d.o.f. by the within/de-meaned estimator.<br>
&gt;<br>
&gt; This is not gretl-specific, of course.<br>
&gt;<br>
&gt; hth,<br>
&gt; sven<br>
&gt; _______________________________________________<br>
&gt; Gretl-users mailing list<br>
&gt; <a href="mailto:Gretl-users@...">Gretl-users@...</a><br>
&gt; <a href="http://lists.wfu.edu/mailman/listinfo/gretl-users" rel="noreferrer" target="_blank">http://lists.wfu.edu/mailman/listinfo/gretl-users</a><br>
&gt;<br>
&gt;<br>
&gt;<br>
&gt; ------------------------------<br>
&gt;<br>
&gt; _______________________________________________<br>
&gt; Gretl-users mailing list<br>
&gt; <a href="mailto:Gretl-users@...">Gretl-users@...</a><br>
&gt; <a href="http://lists.wfu.edu/mailman/listinfo/gretl-users" rel="noreferrer" target="_blank">http://lists.wfu.edu/mailman/listinfo/gretl-users</a><br>
&gt;<br>
&gt; End of Gretl-users Digest, Vol 114, Issue 8<br>
&gt; *******************************************<br>
&gt;<br>
-------------- next part --------------<br>
An HTML attachment was scrubbed...<br>
URL: &lt;<a href="http://lists.wfu.edu/pipermail/gretl-users/attachments/20160720/6a541a0b/attachment-0001.html" rel="noreferrer" target="_blank">http://lists.wfu.edu/pipermail/gretl-users/attachments/20160720/6a541a0b/attachment-0001.html</a>&gt;<br><br>
------------------------------<br><br>
Message: 2<br>
Date: Wed, 20 Jul 2016 19:55:13 +0200<br>
From: Sven Schreiber &lt;<a href="mailto:svetosch@...">svetosch <at> gmx.net</a>&gt;<br>
To: <a href="mailto:gretl-users@...">gretl-users@...</a><br>
Subject: Re: [Gretl-users] Gretl-users Digest, Vol 114, Issue 8<br>
Message-ID: &lt;<a href="mailto:bfdce3ac-706f-9d47-9dce-55c3c180622b <at> gmx.net">bfdce3ac-706f-9d47-9dce-55c3c180622b@...</a>&gt;<br>
Content-Type: text/plain; charset=windows-1252; format=flowed<br><br>
Am 20.07.2016 um 18:50 schrieb George Matysiak:<br>
&gt; Sven, thanks for the reply. Your suggestions do not work - I still get<br>
&gt; the March 2016 files.<br>
&gt;<br><br>
Well if you really deleted the old files manually it sounds very<br>
improbable to me that gretl would download them again. So I guess the<br>
old files must still be lying around on your hard disk somewhere where<br>
gretl is looking for them. Unfortunately right now I'm not sure exactly<br>
what those locations could be.<br><br>
In any case, if you need to look at the new files they are also here:<br><a href="https://sourceforge.net/projects/gretl/files/manual/" rel="noreferrer" target="_blank">https://sourceforge.net/projects/gretl/files/manual/</a><br><br>
cheers,<br>
sven<br><br><br><br>
------------------------------<br><br>
Message: 3<br>
Date: Wed, 20 Jul 2016 14:21:45 -0400 (EDT)<br>
From: Allin Cottrell &lt;<a href="mailto:cottrell@...">cottrell <at> wfu.edu</a>&gt;<br>
To: Gretl list &lt;<a href="mailto:gretl-users@...">gretl-users <at> lists.wfu.edu</a>&gt;<br>
Subject: Re: [Gretl-users] Gretl-users Digest, Vol 114, Issue 8<br>
Message-ID: &lt;<a href="mailto:alpine.LFD.2.20.3.1607201404530.2507 <at> myrtle.attlocal.net">alpine.LFD.2.20.3.1607201404530.2507@...</a>&gt;<br>
Content-Type: text/plain; charset=US-ASCII; format=flowed<br><br>
On Wed, 20 Jul 2016, George Matysiak wrote:<br><br>
&gt; Sven, thanks for the reply. Your suggestions do not work - I still<br>
&gt; get the March 2016 files.<br><br>
Ah, I think I know what may be happening here. Have you at some<br>
point selected A4-format documentation? (Under<br>
/Tools/Preferences/General there's an item "PDF manual preference"<br>
where you can select US letter paper or A4 paper.)<br><br>
Here's the thing: each release package includes current versions of<br>
the Gretl User's Guide and the Gretl Command Reference (PDF files)<br>
in US letter format. But if you want the A4 versions they are<br>
downloaded on demand. And in this respect there's a gap in our<br>
updating logic: if you have once downloaded (for example) the A4<br>
User's Guide, then it will be found on your system thereafter and<br>
will not be downloaded again, even if it goes out of date.<br>
Uninstalling gretl won't help: the old A4 PDF files will not get<br>
deleted since they were not part of the initial gretl installation.<br><br>
We need to figure out a proper fix for this, but in the meantime<br>
here are two possible work-arounds:<br><br>
1. Select US letter format under Preferences, and you'll see the new<br>
PDF files that were installed with gretl 2016c.<br><br>
2. Manually delete the old PDF files under the "doc" folder in your<br>
gretl installation. Then when you go to consult them the new<br>
versions will get downloaded from sourceforge.<br><br>
On the other hand, if the Preferences/General dialog is NOT showing<br>
A4 as your preferred PDF format, then I don't know what's happening.<br>
I have verified that the 2016c release files on sourceforge contain<br>
the Guide and Reference as of July 6, 2016.<br><br>
Allin Cottrell<br><br><br>
------------------------------<br><br>
_______________________________________________<br>
Gretl-users mailing list<br><a href="mailto:Gretl-users@...">Gretl-users@...</a><br><a href="http://lists.wfu.edu/mailman/listinfo/gretl-users" rel="noreferrer" target="_blank">http://lists.wfu.edu/mailman/listinfo/gretl-users</a><br><br>
End of Gretl-users Digest, Vol 114, Issue 9<br>
*******************************************<br>
</blockquote>
</div>
<br>
</div>
</div>
George Matysiak | 20 Jul 18:50 2016
Picon

Re: Gretl-users Digest, Vol 114, Issue 8

Sven, thanks for the reply. Your suggestions do not work - I still get the March 2016 files.


Contact number +48 781 415 432

"In God we trust, all others bring data."

On 20 July 2016 at 17:00, <gretl-users-request-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org> wrote:
Send Gretl-users mailing list submissions to
        gretl-users-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org

To subscribe or unsubscribe via the World Wide Web, visit
        http://lists.wfu.edu/mailman/listinfo/gretl-users
or, via email, send a message with subject or body 'help' to
        gretl-users-request-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org

You can reach the person managing the list at
        gretl-users-owner-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org

When replying, please edit your Subject line so it is more specific
than "Re: Contents of Gretl-users digest..."


Today's Topics:

   1. Re: User Guide Versionand other documentation and Gretl 2016c
      (Sven Schreiber)
   2. Re: F-test: Fixed Effects vs Pooled OLS (Sven Schreiber)
   3. Re: F-test: Fixed Effects vs Pooled OLS (Bruno Gobeil)


----------------------------------------------------------------------

Message: 1
Date: Wed, 20 Jul 2016 16:27:05 +0200
From: Sven Schreiber <svetosch <at> gmx.net>
To: gretl-users-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org
Subject: Re: [Gretl-users] User Guide Versionand other documentation
        and Gretl 2016c
Message-ID: <f581fb81-6b98-a1ea-2ea7-16167705c9ac-hi6Y0CQ0nG0@public.gmane.org>
Content-Type: text/plain; charset=windows-1252; format=flowed

Am 16.07.2016 um 23:41 schrieb George Matysiak:
> Having installed Gretl 2016c I notice that the User Guide is dated March
> 2016, as is the Command Reference, Hansl Primer and Package Function
> Guide. Are the latest versions not automatically installed on a Gretl
> upodate? Thanks.
>

Sorry for the non-response, apparently it's vacation time. I presume
you're using Windows. If you uninstall the old gretl version first, then
it should be the latest pdf versions. If you're as lazy as I am and
simply install the new version over the old one then not necessarily.
You could manually delete the pdfs and then gretl will (try to) download
the current versions when you select the corresponding menu items.

cheers,
sven


------------------------------

Message: 2
Date: Wed, 20 Jul 2016 16:35:33 +0200
From: Sven Schreiber <svetosch <at> gmx.net>
To: gretl-users-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org
Subject: Re: [Gretl-users] F-test: Fixed Effects vs Pooled OLS
Message-ID: <4ce96501-77fa-eb0b-ce9c-da970cd4a2d0-hi6Y0CQ0nG0@public.gmane.org>
Content-Type: text/plain; charset=windows-1252; format=flowed

Am 20.07.2016 um 15:28 schrieb Bruno Gobeil:
> Hello!
>
>
>
> I would like to better understand the rational for using the following
> formula for determining the denominator degrees of freedom for the
> F-test: n(t-1)-(k-1); where n is the number of regions, t the number of
> years, k the number of parameters, including the constant. I thought
> that the use of the de-meaned data approach compared to LSDV approach
> for the fixed effects model would lead to a higher number of denominator
> degrees of freedom, as suggested in the Gretl Guide, with the following
> formula: nt-k.
>

If I understand your question correctly, then here is my answer: LSDV
and de-meaned data fixed effects ("within" estimation) are equivalent
for testing purposes. To put it differently, de-meaning is also a
statistical estimation procedure, because you do not know the expected
population values a priori and hence you have to estimate them via the
arithmetic means. Hence you cannot gain d.o.f. by the within/de-meaned
estimator.

This is not gretl-specific, of course.

hth,
sven


------------------------------

Message: 3
Date: Wed, 20 Jul 2016 14:41:00 +0000
From: Bruno Gobeil <bruno.gobeil-rcFuL2VrcYPQT0dZR+AlfA@public.gmane.org>
To: Gretl list <gretl-users <at> lists.wfu.edu>
Subject: Re: [Gretl-users] F-test: Fixed Effects vs Pooled OLS
Message-ID:
        <BLUPR0401MB1713A32523F2BE9B4BE69955EB080-5qFpKo6KU/BM9wVdnrCY+/nBZW37Ciw+nBOFsp37pqbUKgpGm//BTAC/G2K4zDHf@public.gmane.org>

Content-Type: text/plain; charset="iso-8859-1"

Thanks very much for your quick response. It is much appreciated.

Regards,

Bruno Gobeil
Senior Consultant | Consultant principal
DUNSKY ENERGY CONSULTING | DUNSKY EXPERTISE EN ?NERGIE
[t] 514.504.9030??*26?? [f] 514.289.2665?? [e] bruno.gobeil-rcFuL2VrcYPQT0dZR+AlfA@public.gmane.org



NOTICE: This message (including any attachments) is intended for the sole use of the individual or entity to which it is addressed, and contains information that is privileged, confidential and exempt from disclosure. ?Barring explicit indication to the contrary in the text of the message, any copying, distribution or dissemination of any part of this email (including any attachments), by the intended or accidental recipient, is strictly prohibited. If you have received this communication in error, please notify us immediately. ?Thank You.?

AVIS?: Ce message (et les pi?ces qui y sont jointes) est destin? ? l'usage exclusif de la personne ou de l'entit? ? laquelle il est adress?, et renferme des renseignements privil?gi?s et confidentiels qui ne doivent pas ?tre divulgu?s. Sauf si le message invite explicitement au contraire, il est strictement interdit de copier, distribuer ou diffuser cette communication (et les pi?ces qui y sont jointes), en tout ou en partie, cette interdiction s'appliquant tant au r?cipiendaire voulu qu'involontaire.? Si vous avez re?u cette communication par erreur, veuillez nous en aviser imm?diatement. ?Merci.?

-----Original Message-----
From: gretl-users-bounces-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org [mailto:gretl-users-bounces-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org] On Behalf Of Sven Schreiber
Sent: July 20, 2016 10:36 AM
To: gretl-users-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org
Subject: Re: [Gretl-users] F-test: Fixed Effects vs Pooled OLS

Am 20.07.2016 um 15:28 schrieb Bruno Gobeil:
> Hello!
>
>
>
> I would like to better understand the rational for using the following
> formula for determining the denominator degrees of freedom for the
> F-test: n(t-1)-(k-1); where n is the number of regions, t the number
> of years, k the number of parameters, including the constant. I
> thought that the use of the de-meaned data approach compared to LSDV
> approach for the fixed effects model would lead to a higher number of
> denominator degrees of freedom, as suggested in the Gretl Guide, with
> the following
> formula: nt-k.
>

If I understand your question correctly, then here is my answer: LSDV and de-meaned data fixed effects ("within" estimation) are equivalent for testing purposes. To put it differently, de-meaning is also a statistical estimation procedure, because you do not know the expected population values a priori and hence you have to estimate them via the arithmetic means. Hence you cannot gain d.o.f. by the within/de-meaned estimator.

This is not gretl-specific, of course.

hth,
sven
_______________________________________________
Gretl-users mailing list
Gretl-users-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org
http://lists.wfu.edu/mailman/listinfo/gretl-users



------------------------------

_______________________________________________
Gretl-users mailing list
Gretl-users-npDYnXcwJHngpn9g0Uvcdg@public.gmane.org
http://lists.wfu.edu/mailman/listinfo/gretl-users

End of Gretl-users Digest, Vol 114, Issue 8
*******************************************

<div>
<div dir="ltr"><div class="gmail_default">Sven, thanks for the reply. Your suggestions do not work - I still get the March 2016 files.<br>
</div></div>
<div class="gmail_extra">
<br clear="all"><div><div class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr">
<div><br></div>
<span>Contact number +48 781 415 432<br><br></span>"In God we trust, all others bring data."</div></div></div></div></div></div></div></div></div></div></div></div></div>
<br><div class="gmail_quote">On 20 July 2016 at 17:00,  <span dir="ltr">&lt;<a href="mailto:gretl-users-request@..." target="_blank">gretl-users-request@...</a>&gt;</span> wrote:<br><blockquote class="gmail_quote">Send Gretl-users mailing list submissions to<br>
&nbsp; &nbsp; &nbsp; &nbsp; <a href="mailto:gretl-users@...">gretl-users@...</a><br><br>
To subscribe or unsubscribe via the World Wide Web, visit<br>
&nbsp; &nbsp; &nbsp; &nbsp; <a href="http://lists.wfu.edu/mailman/listinfo/gretl-users" rel="noreferrer" target="_blank">http://lists.wfu.edu/mailman/listinfo/gretl-users</a><br>
or, via email, send a message with subject or body 'help' to<br>
&nbsp; &nbsp; &nbsp; &nbsp; <a href="mailto:gretl-users-request@....edu">gretl-users-request@...</a><br><br>
You can reach the person managing the list at<br>
&nbsp; &nbsp; &nbsp; &nbsp; <a href="mailto:gretl-users-owner@...du">gretl-users-owner@...</a><br><br>
When replying, please edit your Subject line so it is more specific<br>
than "Re: Contents of Gretl-users digest..."<br><br><br>
Today's Topics:<br><br>
&nbsp; &nbsp;1. Re: User Guide Versionand other documentation and Gretl 2016c<br>
&nbsp; &nbsp; &nbsp; (Sven Schreiber)<br>
&nbsp; &nbsp;2. Re: F-test: Fixed Effects vs Pooled OLS (Sven Schreiber)<br>
&nbsp; &nbsp;3. Re: F-test: Fixed Effects vs Pooled OLS (Bruno Gobeil)<br><br><br>
----------------------------------------------------------------------<br><br>
Message: 1<br>
Date: Wed, 20 Jul 2016 16:27:05 +0200<br>
From: Sven Schreiber &lt;<a href="mailto:svetosch@...">svetosch <at> gmx.net</a>&gt;<br>
To: <a href="mailto:gretl-users@...">gretl-users@...</a><br>
Subject: Re: [Gretl-users] User Guide Versionand other documentation<br>
&nbsp; &nbsp; &nbsp; &nbsp; and Gretl 2016c<br>
Message-ID: &lt;<a href="mailto:f581fb81-6b98-a1ea-2ea7-16167705c9ac <at> gmx.net">f581fb81-6b98-a1ea-2ea7-16167705c9ac@...</a>&gt;<br>
Content-Type: text/plain; charset=windows-1252; format=flowed<br><br>
Am 16.07.2016 um 23:41 schrieb George Matysiak:<br>
&gt; Having installed Gretl 2016c I notice that the User Guide is dated March<br>
&gt; 2016, as is the Command Reference, Hansl Primer and Package Function<br>
&gt; Guide. Are the latest versions not automatically installed on a Gretl<br>
&gt; upodate? Thanks.<br>
&gt;<br><br>
Sorry for the non-response, apparently it's vacation time. I presume<br>
you're using Windows. If you uninstall the old gretl version first, then<br>
it should be the latest pdf versions. If you're as lazy as I am and<br>
simply install the new version over the old one then not necessarily.<br>
You could manually delete the pdfs and then gretl will (try to) download<br>
the current versions when you select the corresponding menu items.<br><br>
cheers,<br>
sven<br><br><br>
------------------------------<br><br>
Message: 2<br>
Date: Wed, 20 Jul 2016 16:35:33 +0200<br>
From: Sven Schreiber &lt;<a href="mailto:svetosch@...">svetosch <at> gmx.net</a>&gt;<br>
To: <a href="mailto:gretl-users@...">gretl-users@...</a><br>
Subject: Re: [Gretl-users] F-test: Fixed Effects vs Pooled OLS<br>
Message-ID: &lt;<a href="mailto:4ce96501-77fa-eb0b-ce9c-da970cd4a2d0 <at> gmx.net">4ce96501-77fa-eb0b-ce9c-da970cd4a2d0@...</a>&gt;<br>
Content-Type: text/plain; charset=windows-1252; format=flowed<br><br>
Am 20.07.2016 um 15:28 schrieb Bruno Gobeil:<br>
&gt; Hello!<br>
&gt;<br>
&gt;<br>
&gt;<br>
&gt; I would like to better understand the rational for using the following<br>
&gt; formula for determining the denominator degrees of freedom for the<br>
&gt; F-test: n(t-1)-(k-1); where n is the number of regions, t the number of<br>
&gt; years, k the number of parameters, including the constant. I thought<br>
&gt; that the use of the de-meaned data approach compared to LSDV approach<br>
&gt; for the fixed effects model would lead to a higher number of denominator<br>
&gt; degrees of freedom, as suggested in the Gretl Guide, with the following<br>
&gt; formula: nt-k.<br>
&gt;<br><br>
If I understand your question correctly, then here is my answer: LSDV<br>
and de-meaned data fixed effects ("within" estimation) are equivalent<br>
for testing purposes. To put it differently, de-meaning is also a<br>
statistical estimation procedure, because you do not know the expected<br>
population values a priori and hence you have to estimate them via the<br>
arithmetic means. Hence you cannot gain d.o.f. by the within/de-meaned<br>
estimator.<br><br>
This is not gretl-specific, of course.<br><br>
hth,<br>
sven<br><br><br>
------------------------------<br><br>
Message: 3<br>
Date: Wed, 20 Jul 2016 14:41:00 +0000<br>
From: Bruno Gobeil &lt;<a href="mailto:bruno.gobeil@...">bruno.gobeil@...</a>&gt;<br>
To: Gretl list &lt;<a href="mailto:gretl-users@...">gretl-users <at> lists.wfu.edu</a>&gt;<br>
Subject: Re: [Gretl-users] F-test: Fixed Effects vs Pooled OLS<br>
Message-ID:<br>
&nbsp; &nbsp; &nbsp; &nbsp; &lt;<a href="mailto:BLUPR0401MB1713A32523F2BE9B4BE69955EB080@...">BLUPR0401MB1713A32523F2BE9B4BE69955EB080@...</a>&gt;<br><br>
Content-Type: text/plain; charset="iso-8859-1"<br><br>
Thanks very much for your quick response. It is much appreciated.<br><br>
Regards,<br><br>
Bruno Gobeil<br>
Senior Consultant | Consultant principal<br>
DUNSKY ENERGY CONSULTING | DUNSKY EXPERTISE EN ?NERGIE<br>
[t] 514.504.9030??*26?? [f] 514.289.2665?? [e] <a href="mailto:bruno.gobeil@...">bruno.gobeil@...</a><br><br><br><br>
NOTICE: This message (including any attachments) is intended for the sole use of the individual or entity to which it is addressed, and contains information that is privileged, confidential and exempt from disclosure. ?Barring explicit indication to the contrary in the text of the message, any copying, distribution or dissemination of any part of this email (including any attachments), by the intended or accidental recipient, is strictly prohibited. If you have received this communication in error, please notify us immediately. ?Thank You.?<br><br>
AVIS?: Ce message (et les pi?ces qui y sont jointes) est destin? ? l'usage exclusif de la personne ou de l'entit? ? laquelle il est adress?, et renferme des renseignements privil?gi?s et confidentiels qui ne doivent pas ?tre divulgu?s. Sauf si le message invite explicitement au contraire, il est strictement interdit de copier, distribuer ou diffuser cette communication (et les pi?ces qui y sont jointes), en tout ou en partie, cette interdiction s'appliquant tant au r?cipiendaire voulu qu'involontaire.? Si vous avez re?u cette communication par erreur, veuillez nous en aviser imm?diatement. ?Merci.?<br><br>
-----Original Message-----<br>
From: <a href="mailto:gretl-users-bounces@...">gretl-users-bounces@...</a> [mailto:<a href="mailto:gretl-users-bounces <at> lists.wfu.edu">gretl-users-bounces@...</a>] On Behalf Of Sven Schreiber<br>
Sent: July 20, 2016 10:36 AM<br>
To: <a href="mailto:gretl-users@...">gretl-users@...</a><br>
Subject: Re: [Gretl-users] F-test: Fixed Effects vs Pooled OLS<br><br>
Am 20.07.2016 um 15:28 schrieb Bruno Gobeil:<br>
&gt; Hello!<br>
&gt;<br>
&gt;<br>
&gt;<br>
&gt; I would like to better understand the rational for using the following<br>
&gt; formula for determining the denominator degrees of freedom for the<br>
&gt; F-test: n(t-1)-(k-1); where n is the number of regions, t the number<br>
&gt; of years, k the number of parameters, including the constant. I<br>
&gt; thought that the use of the de-meaned data approach compared to LSDV<br>
&gt; approach for the fixed effects model would lead to a higher number of<br>
&gt; denominator degrees of freedom, as suggested in the Gretl Guide, with<br>
&gt; the following<br>
&gt; formula: nt-k.<br>
&gt;<br><br>
If I understand your question correctly, then here is my answer: LSDV and de-meaned data fixed effects ("within" estimation) are equivalent for testing purposes. To put it differently, de-meaning is also a statistical estimation procedure, because you do not know the expected population values a priori and hence you have to estimate them via the arithmetic means. Hence you cannot gain d.o.f. by the within/de-meaned estimator.<br><br>
This is not gretl-specific, of course.<br><br>
hth,<br>
sven<br>
_______________________________________________<br>
Gretl-users mailing list<br><a href="mailto:Gretl-users@...">Gretl-users@...</a><br><a href="http://lists.wfu.edu/mailman/listinfo/gretl-users" rel="noreferrer" target="_blank">http://lists.wfu.edu/mailman/listinfo/gretl-users</a><br><br><br><br>
------------------------------<br><br>
_______________________________________________<br>
Gretl-users mailing list<br><a href="mailto:Gretl-users@...">Gretl-users@...</a><br><a href="http://lists.wfu.edu/mailman/listinfo/gretl-users" rel="noreferrer" target="_blank">http://lists.wfu.edu/mailman/listinfo/gretl-users</a><br><br>
End of Gretl-users Digest, Vol 114, Issue 8<br>
*******************************************<br>
</blockquote>
</div>
<br>
</div>
</div>
Bruno Gobeil | 20 Jul 15:28 2016

F-test: Fixed Effects vs Pooled OLS

Hello!

 

I would like to better understand the rational for using the following formula for determining the denominator degrees of freedom for the F-test: n(t-1)-(k-1); where n is the number of regions, t the number of years, k the number of parameters, including the constant. I thought that the use of the de-meaned data approach compared to LSDV approach for the fixed effects model would lead to a higher number of denominator degrees of freedom, as suggested in the Gretl Guide, with the following formula: nt-k.

 

I would greatly appreciate if someone could shed some light on the matter.

 

Thank you   

 

Bruno Gobeil

Senior Consultant | Consultant principal

DUNSKY ENERGY CONSULTING | DUNSKY EXPERTISE EN ÉNERGIE

[t] 514.504.9030  *26   [f] 514.289.2665   [e] bruno.gobeil-rcFuL2VrcYPQT0dZR+AlfA@public.gmane.org

 

 

NOTICE: This message (including any attachments) is intended for the sole use of the individual or entity to which it is addressed, and contains information that is privileged, confidential and exempt from disclosure.  Barring explicit indication to the contrary in the text of the message, any copying, distribution or dissemination of any part of this email (including any attachments), by the intended or accidental recipient, is strictly prohibited. If you have received this communication in error, please notify us immediately.  Thank You. 

 

AVIS : Ce message (et les pièces qui y sont jointes) est destiné à l'usage exclusif de la personne ou de l'entité à laquelle il est adressé, et renferme des renseignements privilégiés et confidentiels qui ne doivent pas être divulgués. Sauf si le message invite explicitement au contraire, il est strictement interdit de copier, distribuer ou diffuser cette communication (et les pièces qui y sont jointes), en tout ou en partie, cette interdiction s’appliquant tant au récipiendaire voulu qu’involontaire.  Si vous avez reçu cette communication par erreur, veuillez nous en aviser immédiatement.  Merci. 

 

<div>
<div class="WordSection1">
<p class="MsoNormal"><span lang="FR-CA">Hello!<p></p></span></p>
<p class="MsoNormal"><span lang="FR-CA"><p>&nbsp;</p></span></p>
<p class="MsoNormal">I would like to better understand the rational for using the following formula for determining the denominator degrees of freedom for the F-test: n(t-1)-(k-1); where n is the number of regions, t the number of years, k the number of parameters,
 including the constant. I thought that the use of the de-meaned data approach compared to LSDV approach for the fixed effects model would lead to a higher number of denominator degrees of freedom, as suggested in the Gretl Guide, with the following formula:
 nt-k.<p></p></p>
<p class="MsoNormal"><p>&nbsp;</p></p>
<p class="MsoNormal">I would greatly appreciate if someone could shed some light on the matter.<p></p></p>
<p class="MsoNormal"><p>&nbsp;</p></p>
<p class="MsoNormal">Thank you &nbsp;&nbsp;<p></p></p>
<p class="MsoNormal"><p>&nbsp;</p></p>
<p class="MsoNormal"><span>Bruno Gobeil<p></p></span></p>
<p class="MsoNormal"><span>Senior Consultant
</span><span>| </span>
<span>Consultant principal<p></p></span></p>
<p class="MsoNormal"><span>DU</span><span lang="FR-CA">NSKY ENERGY CONSULTING
</span><span lang="FR-CA">|
</span><span lang="FR-CA">DUNSKY EXPERTISE EN &Eacute;NERGIE</span><span lang="FR-CA">
</span><span lang="FR-CA"><p></p></span></p>
<p class="MsoNormal"><span lang="FR-CA">[t]</span><span lang="FR-CA">
</span><span lang="FR-CA">514.504.9030&nbsp;&nbsp;*26&nbsp;&nbsp;
</span><span lang="FR-CA">[f]</span><span lang="FR-CA">
</span><span lang="FR-CA">514.289.2665&nbsp;&nbsp;
</span><span lang="FR-CA">[e]</span><span lang="FR-CA">
</span><span lang="FR-CA"><a href="mailto:bruno.gobeil@..."><span>bruno.gobeil@...</span></a></span><span lang="FR-CA"><p></p></span></p>
<p class="MsoNormal"><span lang="FR-CA"><p>&nbsp;</p></span></p>
<p class="MsoNormal"><span lang="FR-CA"><a href="http://www.dunsky.com/"><span lang="EN-CA"></span></a></span><span lang="FR-CA"><p></p></span></p>
<p class="MsoNormal"><span lang="FR-CA"><p>&nbsp;</p></span></p>
<p class="MsoNormal"><span lang="EN-US">NOTICE: This message (including any attachments) is intended for the sole use of the individual or entity to which it
 is addressed, and contains information that is privileged, confidential and exempt from disclosure. &nbsp;Barring explicit indication to the contrary in the text of the message, any copying, distribution or dissemination of any part of this email (including any
 attachments), by the intended or accidental recipient, is strictly prohibited. If you have received this communication in error, please notify us immediately. &nbsp;</span><span lang="FR-CA">Thank
 You.&nbsp;<p></p></span></p>
<p class="MsoNormal"><span lang="FR-CA"><p>&nbsp;</p></span></p>
<p class="MsoNormal"><span lang="FR-CA">AVIS&nbsp;: Ce message (et les pi&egrave;ces qui y sont jointes) est destin&eacute; &agrave; l'usage exclusif de la personne ou de l'entit&eacute; &agrave; laquelle
 il est adress&eacute;, et renferme des renseignements privil&eacute;gi&eacute;s et confidentiels qui ne doivent pas &ecirc;tre divulgu&eacute;s. Sauf si le message invite explicitement au contraire, il est strictement interdit de copier, distribuer ou diffuser cette communication (et les pi&egrave;ces
 qui y sont jointes), en tout ou en partie, cette interdiction s&rsquo;appliquant tant au r&eacute;cipiendaire voulu qu&rsquo;involontaire.&nbsp; Si vous avez re&ccedil;u cette communication par erreur, veuillez nous en aviser imm&eacute;diatement. &nbsp;Merci.&nbsp;
<p></p></span></p>
<p class="MsoNormal"><span lang="FR-CA"><p>&nbsp;</p></span></p>
</div>
</div>
George Matysiak | 16 Jul 23:41 2016
Picon

Re: User Guide Versionand other documentation and Gretl 2016c

Having installed Gretl 2016c I notice that the User Guide is dated March 2016, as is the Command Reference, Hansl Primer and Package Function Guide. Are the latest versions not automatically installed on a Gretl upodate? Thanks.

George


<div><div dir="ltr">
<div class="gmail_default">Having installed Gretl 2016c I notice that the User Guide is dated March 2016, as is the Command Reference, Hansl Primer and Package Function Guide. Are the latest versions not automatically installed on a Gretl upodate? Thanks.<br><br>
</div>
<div class="gmail_default">George <br clear="all">
</div>
<div><div class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr">
<div><br></div>
<br>
</div></div></div></div></div></div></div></div></div></div></div></div></div>
</div></div>
Wingenroth, Thorsten | 16 Jul 08:32 2016
Picon

Screencasting Tool

Hi Clive,

 

you were looking for a screencasting tool.

I came across ActivePresenter as screencasting tool. It’s free as long as you only output video and it’s highly professional.

I used it for a couple of screencasts and it is really comfortable. You can split your video, make certain screens appear longer, highlight and do voice recording afterwards and during capture, as you wish.

 

Here is the link: http://atomisystems.com/

 

Kind regards,

 

Thorsten

 

 

<div>
<div class="WordSection1">
<p class="MsoNormal">Hi Clive,<p></p></p>
<p class="MsoNormal"><p>&nbsp;</p></p>
<p class="MsoNormal"><span lang="EN-US">you were looking for a screencasting tool.<p></p></span></p>
<p class="MsoNormal"><span lang="EN-US">I came across ActivePresenter as screencasting tool. It&rsquo;s free as long as you only output video and it&rsquo;s highly professional.<p></p></span></p>
<p class="MsoNormal"><span lang="EN-US">I used it for a couple of screencasts and it is really comfortable. You can split your video, make certain screens appear longer, highlight and do voice recording afterwards and during capture, as you wish.<p></p></span></p>
<p class="MsoNormal"><span lang="EN-US"><p>&nbsp;</p></span></p>
<p class="MsoNormal"><span lang="EN-US">Here is the link: <a href="http://atomisystems.com/">
http://atomisystems.com/</a><p></p></span></p>
<p class="MsoNormal"><span lang="EN-US"><p>&nbsp;</p></span></p>
<p class="MsoNormal"><span lang="EN-US">Kind regards,<p></p></span></p>
<p class="MsoNormal"><span lang="EN-US"><p>&nbsp;</p></span></p>
<p class="MsoNormal"><span lang="EN-US">Thorsten<p></p></span></p>
<p class="MsoNormal"><span lang="EN-US"><p>&nbsp;</p></span></p>
<p class="MsoNormal"><span lang="EN-US"><p>&nbsp;</p></span></p>
</div>
</div>
Allin Cottrell | 6 Jul 18:22 2016
Picon

gretl 2016c released

See
https://sourceforge.net/projects/gretl/files/gretl/2016c/

Allin Cottrell
Allin Cottrell | 1 Jul 19:37 2016
Picon

plottting with --band option: a follow-up

In my recent posting at
http://lists.wfu.edu/pipermail/gretl-users/2016-June/011934.html
I wasn't precise enough about the handling of the --band option when 
the data are supplied in the form of a matrix or matrices.

In fact, this differs depending on whether you are using the 
traditional "gnuplot" command or the new(ish) "plot" block. That's 
because in the first case the supplied matrix is treated as a mini 
dataset (and you index into it for the columns you want), while with 
"plot" an initial matrix argument is taken as the data to plot (no 
indexing required, or even permitted).

Anyway, here's an illustrative script (based on one devised by Jack 
to point out the problem in my exposition, for which thanks):

<hansl>
scalar n = 20
scalar x = 7.5
matrix A = x ~ seq(1,n)'         # the data to plot
matrix B = x ~ sqrt(seq(3,n+2)') # the band information

# block style: you need two matrices with --band
plot A
     option band=B
end plot --output=display

# traditional style: you select columns of a single matrix
matrix C = A ~ sqrt(seq(3,n+2)')
gnuplot 1 2 --matrix=C --output=display --band=1,3
</hansl>

The two plots should be identical, but they require slightly 
different routes for their production.

Allin Cottrell

Ernesto Armijo | 1 Jul 17:12 2016
Picon

Conditional Logit

Hi everyone. I was wondering if anybody has coded a routine to estimate conditional logits in Gretl. I teach an introductory course one Econometrics and Gretl works perfectly for everything except this. I don't want to use R (again :-)

REgards,

Ernesto
<div><div dir="ltr">Hi everyone. I was wondering if anybody has coded a routine to estimate conditional logits in Gretl. I teach an introductory course one Econometrics and Gretl works perfectly for everything except this. I don't want to use R (again :-)<div><br></div>
<div>REgards,</div>
<div><br></div>
<div>Ernesto</div> 		 	   		  </div></div>
Andreas Zervas | 30 Jun 11:45 2016
Picon

strange behavior

Hi all,

I am attaching two scripts that produce a behavior that puzzles me. test.inp makes some series and calls test_fcn.inp; the latter  has 2 functions that produce lags for a list of variables and for matrices. Under Windows 7 & 8 (and Gretl 2015d in both machines) the code runs - it is an old code since 2011 and Gretl 1.9.5 I think. However, the function for lists is not working in Linux (Ubuntu 15.10 + Gretl 1.10.1) and I can not understand why.

The problem seems more general, as other functions that I have work with matrix arguments but not with list arguments in Linux.

Any suggestions?

Thank you for your time and effort.

Andreas

Attachment (test.inp): text/gretl.script, 337 bytes
Attachment (test_fcn.inp): text/gretl.script, 3271 bytes
<div><div>
<div>Hi all,</div>
<div><br></div>
<div dir="ltr">I am attaching two scripts that produce a behavior that puzzles me. test.inp makes some series and calls test_fcn.inp; the latter&nbsp; has 2 functions that produce lags for a list of variables and for matrices. Under Windows 7 &amp; 8 (and Gretl 2015d in both machines) the code runs - it is an old code since 2011 and Gretl 1.9.5 I think. However, the function for lists is not working in Linux (Ubuntu 15.10 + Gretl 1.10.1) and I can not understand why. <br>
</div>
<div dir="ltr"><br></div>
<div dir="ltr">The problem seems more general, as other functions that I have work with matrix arguments but not with list arguments in Linux.</div>
<div dir="ltr"><br></div>
<div dir="ltr">Any suggestions?</div>
<div dir="ltr"><br></div>
<div dir="ltr">Thank you for your time and effort.</div>
<div dir="ltr"><br></div>
<div dir="ltr">Andreas<br>
</div>
<div><br></div>
</div></div>

Gmane