New mailing list? (was Re: Johansen question)
by Allin Cottrell
On Mon, 2 May 2011, Sven Schreiber wrote:
> Before creating a new list for discussion of econometrics, maybe it
> would be worthwhile to check if another list already serves the same
> purpose (see for example
> http://www.feweb.vu.nl/econometriclinks/mailing/).
Good idea, but it seems there isn't such a thing.
> Even if we come to the conclusion that there is a niche to be
> filled, maybe it would make sense to at least coordinate with
> the R people?
Possibly -- though it seems there are tons of R lists so I don't
know how interested they'd be.
> OTOH, I'm not overly enthusiastic to have general econometric
> discussions on gretl-users. It's true that the traffic here is
> not high, and this is also due to the fact that in the past
> off-topic (=not gretl-specific) questions have been discouraged.
> But this low traffic makes it possible that a relevant number of
> subscribers are actually following most (if not all) threads. I
> fear that if general econometric questions are discussed (which
> I believe will be quite basic most of the time) then some people
> might pay less attention to the list in general, with
> detrimental effects on the gretl-specific issues.
I think this point is well made. I'm still mulling the issue over,
but I tend to agree with you.
Allin Cottrell
13 years
- 5
- 4
Re: [Gretl-users] Johansen question
by MICHAEL BOLDIN
>>For a bivariate case, if the trace test rejects c=0 and does not
>>reject c=1, I report c=1. If it is the other way around, then I report
>>c=0 as the test result.
>>As you know, sometimes the results can be contradictory so that c=0
>>and c=1 are rejected (or not rejected) simultaneously.
>>My question is that would it be OK to report "inconclusive" in those
>>cases? Or am I expected to follow another further procedure?
Three things to think about (might make you recognize that your case
is more common than many realize):
1.You are searching for results using different lag numbers and the
null hypothesis probabilities are based on knowing the right lag
number beforehand. Of course no one knows the right lag number in a
real study (only known in constructed data cases), but once you
perform a search you should be willing to be skeptical of the test
statistic probabilities.
2. Not rejecting both c=0 and =1 is not an anomaly if you understand
you are only computing the odds each hypothesis is incorrect. You are
not computing the odds of 'correctness' given the results from the
other test. Failing to reject at the 5% level is just that-- failure
to say an hypothesis is blatantly wrong (+ recognizing point 1 that
the 5% number may be misleading).
3. Deciding c=1 vs c=0, i.e. testing whether two time series need to
be differenced or do not need to be differenced to create a stationary
cointegrating relationship is often not as interesting or
controversial as researchers believe it is. Assuming you are only
constructing the co-integrating vector for modeling purposes and this
is a first step, you might find similar results either way. Or once
one understands the data and its source you might conclude c=0 or c=1
is implausible. For example, one might reject c=0 and accept c=1 (or
vice-versa) when testing whether the UK and the US$ price levels are
cointegrated, when the true answer depends on how accurately the price
levels are computed. (I.e. I'd argue they must be differenced at
least once to control for measurement differences before seeing any
Johansen tests.)
(this post might be considered a test of whether an econometric
methodology list connected to GRETL would be worthwhile or fills a
need).
13 years
- 7
- 8
Re: [Gretl-users] Johansen question
by Allin Cottrell
On Sun, 1 May 2011, Talha Yalta wrote:
> I want to add a table which will show Johansen tests can give
> different results in small samples when different parameters are used.
> In the table, I just use the trace test results (since this is just to
> prove a point) and choose lags 1, 2, and 3. I also use the default
> case as well as the --ct option. This results in 6 combinations.
>
> Here is how I proceed:
>
> For a bivariate case, if the trace test rejects c=0 and does not
> reject c=1, I report c=1.
OK.
> If it is the other way around, then I report c=0 as the test
> result.
On the trace test, that result would seem anomalous, and
indicative of a small-sample problem. If there's "enough evidence"
to reject c=1 (with an alternative of c=2), then concluding that
c=0 is problematic.
> As you know, sometimes the results can be contradictory so that c=0
> and c=1 are rejected (or not rejected) simultaneously.
That doesn't seem contradictory: if both c=0 and c=1 are rejected,
that favors the hypothesis that both series are stationary. If
neither c=0 nor c=1 is rejected that suggests they're both
non-stationary, and not cointegrated.
Allin Cottrell
13 years
- 6
- 8
Re: [Gretl-users] Johansen question
by Olle Olsson
I agree that a separate Gretl-methods list is a good idea.
/Olle
On Mon, May 2, 2011 at 12:01 PM, <gretl-users-request(a)lists.wfu.edu> wrote:
> Send Gretl-users mailing list submissions to
> gretl-users(a)lists.wfu.edu
>
> 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(a)lists.wfu.edu
>
> You can reach the person managing the list at
> gretl-users-owner(a)lists.wfu.edu
>
> When replying, please edit your Subject line so it is more specific
> than "Re: Contents of Gretl-users digest..."
>
>
> Today's Topics:
>
> 1. Re: Johansen question (Summers, Peter)
> 2. Re: Johansen question (Allin Cottrell)
> 3. Re: Johansen question (Summers, Peter)
> 4. Re: Johansen question (Henrique Andrade)
> 5. Re: Johansen question (Talha Yalta)
> 6. Re: Johansen question (Anutechia Asongu)
> 7. Re: scatter plot with non-binary factor separation
> (Ignacio Diaz-Emparanza)
>
>
> ----------------------------------------------------------------------
>
> Message: 1
> Date: Sun, 1 May 2011 18:01:21 -0500
> From: "Summers, Peter" <peter.summers(a)ttu.edu>
> Subject: Re: [Gretl-users] Johansen question
> To: Gretl list <gretl-users(a)lists.wfu.edu>
> Message-ID:
> <8885DA157278484489B1EBC8B8C043E3010AADCBB80D(a)COTTUS.ttu.edu>
> Content-Type: text/plain; charset="us-ascii"
>
> Michael,
>
> Your second point sounds like you're giving a Bayesian posterior
> probability interpretation to a frequentist hypothesis test, and I'm not
> sure that's warranted (it may be -- this is off the top of my head).
> Cointegration is one of the areas that I think makes a lot more sense from a
> Bayesian point of view, but I'll have to do some remedial reading before I
> can say any more about this particular issue.
>
> I guess this also relates to your parenthetical 'point'.
>
> PS
> ________________________________________
> From: gretl-users-bounces(a)lists.wfu.edu [gretl-users-bounces(a)lists.wfu.edu]
> On Behalf Of MICHAEL BOLDIN [mboldin(a)temple.edu]
> Sent: Sunday, May 01, 2011 3:54 PM
> To: gretl-users(a)lists.wfu.edu
> Subject: Re: [Gretl-users] Johansen question
>
> >>For a bivariate case, if the trace test rejects c=0 and does not
> >>reject c=1, I report c=1. If it is the other way around, then I report
> >>c=0 as the test result.
>
> >>As you know, sometimes the results can be contradictory so that c=0
> >>and c=1 are rejected (or not rejected) simultaneously.
>
> >>My question is that would it be OK to report "inconclusive" in those
> >>cases? Or am I expected to follow another further procedure?
>
> Three things to think about (might make you recognize that your case
> is more common than many realize):
>
> 1.You are searching for results using different lag numbers and the
> null hypothesis probabilities are based on knowing the right lag
> number beforehand. Of course no one knows the right lag number in a
> real study (only known in constructed data cases), but once you
> perform a search you should be willing to be skeptical of the test
> statistic probabilities.
>
> 2. Not rejecting both c=0 and =1 is not an anomaly if you understand
> you are only computing the odds each hypothesis is incorrect. You are
> not computing the odds of 'correctness' given the results from the
> other test. Failing to reject at the 5% level is just that-- failure
> to say an hypothesis is blatantly wrong (+ recognizing point 1 that
> the 5% number may be misleading).
>
> 3. Deciding c=1 vs c=0, i.e. testing whether two time series need to
> be differenced or do not need to be differenced to create a stationary
> cointegrating relationship is often not as interesting or
> controversial as researchers believe it is. Assuming you are only
> constructing the co-integrating vector for modeling purposes and this
> is a first step, you might find similar results either way. Or once
> one understands the data and its source you might conclude c=0 or c=1
> is implausible. For example, one might reject c=0 and accept c=1 (or
> vice-versa) when testing whether the UK and the US$ price levels are
> cointegrated, when the true answer depends on how accurately the price
> levels are computed. (I.e. I'd argue they must be differenced at
> least once to control for measurement differences before seeing any
> Johansen tests.)
>
> (this post might be considered a test of whether an econometric
> methodology list connected to GRETL would be worthwhile or fills a
> need).
> _______________________________________________
> Gretl-users mailing list
> Gretl-users(a)lists.wfu.edu
> http://lists.wfu.edu/mailman/listinfo/gretl-users
>
>
>
> ------------------------------
>
> Message: 2
> Date: Sun, 1 May 2011 19:29:00 -0400 (EDT)
> From: Allin Cottrell <cottrell(a)wfu.edu>
> Subject: Re: [Gretl-users] Johansen question
> To: Gretl list <gretl-users(a)lists.wfu.edu>
> Message-ID: <Pine.A41.4.58.1105011915100.663632(a)f1n11.sp2net.wfu.edu>
> Content-Type: TEXT/PLAIN; charset=US-ASCII
>
> On Sun, 1 May 2011, MICHAEL BOLDIN wrote:
>
> > (this post might be considered a test of whether an econometric
> > methodology list connected to GRETL would be worthwhile or fills a
> > need).
>
> That's an interesting question. Participants in the gretl-users
> list are generally tolerant (up to a point) of questions that are
> not really gretl-specific. But general questions of econometric
> methodology don't fall within the currently advertised purpose of
> this list.
>
> I wouldn't mind setting up a parallel list for methodological
> questions (as you say, "connected to gretl") if people think (a)
> that would be useful, and (b) it's better not to use gretl-users
> for this purpose. (If there were another list to which we could
> refer methodological queries we could just do so, but so far as I
> know there isn't really such a thing.)
>
> Thoughts? (And if positive, suggestions for a name for the list?)
>
> Allin Cottrell
>
>
> ------------------------------
>
> Message: 3
> Date: Sun, 1 May 2011 21:10:38 -0500
> From: "Summers, Peter" <peter.summers(a)ttu.edu>
> Subject: Re: [Gretl-users] Johansen question
> To: Gretl list <gretl-users(a)lists.wfu.edu>
> Message-ID:
> <8885DA157278484489B1EBC8B8C043E3010AADCBB80E(a)COTTUS.ttu.edu>
> Content-Type: text/plain; charset="us-ascii"
>
> If positive, how about 'gretl-methods'?
>
> PS
> ________________________________________
> From: gretl-users-bounces(a)lists.wfu.edu [gretl-users-bounces(a)lists.wfu.edu]
> On Behalf Of Allin Cottrell [cottrell(a)wfu.edu]
> Sent: Sunday, May 01, 2011 6:29 PM
> To: Gretl list
> Subject: Re: [Gretl-users] Johansen question
>
> On Sun, 1 May 2011, MICHAEL BOLDIN wrote:
>
> > (this post might be considered a test of whether an econometric
> > methodology list connected to GRETL would be worthwhile or fills a
> > need).
>
> That's an interesting question. Participants in the gretl-users
> list are generally tolerant (up to a point) of questions that are
> not really gretl-specific. But general questions of econometric
> methodology don't fall within the currently advertised purpose of
> this list.
>
> I wouldn't mind setting up a parallel list for methodological
> questions (as you say, "connected to gretl") if people think (a)
> that would be useful, and (b) it's better not to use gretl-users
> for this purpose. (If there were another list to which we could
> refer methodological queries we could just do so, but so far as I
> know there isn't really such a thing.)
>
> Thoughts? (And if positive, suggestions for a name for the list?)
>
> Allin Cottrell
> _______________________________________________
> Gretl-users mailing list
> Gretl-users(a)lists.wfu.edu
> http://lists.wfu.edu/mailman/listinfo/gretl-users
>
>
>
> ------------------------------
>
> Message: 4
> Date: Mon, 2 May 2011 00:02:14 -0300
> From: Henrique Andrade <henrique.coelho(a)gmail.com>
> Subject: Re: [Gretl-users] Johansen question
> To: Gretl list <gretl-users(a)lists.wfu.edu>
> Message-ID: <BANLkTikmR4ExbWFMPXLQgzBnK4ERzXrK7w(a)mail.gmail.com>
> Content-Type: text/plain; charset="iso-8859-1"
>
> Em 1 de maio de 2011 Peter <peter.summers(a)ttu.edu> escreveu:
>
> If positive, how about 'gretl-methods'?
> >
>
> Good suggestion!
>
> Best,
> --
> *Henrique C. de Andrade*
> Doutorando em Economia Aplicada
> Universidade Federal do Rio Grande do Sul
> www.ufrgs.br/ppge
> -------------- next part --------------
> An HTML attachment was scrubbed...
> URL:
> http://lists.wfu.edu/pipermail/gretl-users/attachments/20110502/5371e8cd/...
>
> ------------------------------
>
> Message: 5
> Date: Mon, 2 May 2011 08:14:47 +0300
> From: Talha Yalta <talhayalta(a)gmail.com>
> Subject: Re: [Gretl-users] Johansen question
> To: Gretl list <gretl-users(a)lists.wfu.edu>
> Message-ID: <BANLkTi=TB0ziitgmGp0KpHkguEhMiN0giQ(a)mail.gmail.com>
> Content-Type: text/plain; charset=windows-1252
>
> This would benefit young and relatively less experienced researchers like
> me.
> Cheers
> Talha
>
>
>
> 2011/5/2 Henrique Andrade <henrique.coelho(a)gmail.com>:
> > Em 1 de maio de 2011 Peter <peter.summers(a)ttu.edu> escreveu:
> >>
> >> If positive, how about 'gretl-methods'?
> >
> > Good suggestion!
> > Best,
> > --
> > Henrique C. de Andrade
> > Doutorando em Economia Aplicada
> > Universidade Federal do Rio Grande do Sul
> > www.ufrgs.br/ppge
> >
> > _______________________________________________
> > Gretl-users mailing list
> > Gretl-users(a)lists.wfu.edu
> > http://lists.wfu.edu/mailman/listinfo/gretl-users
> >
>
>
>
> --
> ?An expert is a person who has made all the mistakes that can be made
> in a very narrow field.? - Niels Bohr (1885-1962)
> --
>
>
>
> ------------------------------
>
> Message: 6
> Date: Mon, 2 May 2011 01:43:33 -0700 (PDT)
> From: Anutechia Asongu <simplice_peace(a)yahoo.com>
> Subject: Re: [Gretl-users] Johansen question
> To: Gretl list <gretl-users(a)lists.wfu.edu>
> Message-ID: < <253387.3666.qm(a)web110311.mail.gq1.yahoo.com>253387.3666.
> qm(a)web110311.mail.gq1.yahoo.com>
> Content-Type: text/plain; charset="utf-8"
>
> Me too
>
> --- On Sun, 5/1/11, Talha Yalta <talhayalta(a)gmail.com> wrote:
>
> From: Talha Yalta <talhayalta(a)gmail.com>
> Subject: Re: [Gretl-users] Johansen question
> To: "Gretl list" <gretl-users(a)lists.wfu.edu>
> Date: Sunday, May 1, 2011, 10:14 PM
>
> This would benefit young and relatively less experienced researchers like
> me.
> Cheers
> Talha
>
>
>
> 2011/5/2 Henrique Andrade <henrique.coelho(a)gmail.com>:
> > Em 1 de maio de 2011 Peter <peter.summers(a)ttu.edu> escreveu:
> >>
> >> If positive, how about 'gretl-methods'?
> >
> > Good suggestion!
> > Best,
> > --
> > Henrique C. de Andrade
> > Doutorando em Economia Aplicada
> > Universidade Federal do Rio Grande do Sul
> > www.ufrgs.br/ppge
> >
> > _______________________________________________
> > Gretl-users mailing list
> > Gretl-users(a)lists.wfu.edu
> > http://lists.wfu.edu/mailman/listinfo/gretl-users
> >
>
>
>
> --
> ?An expert is a person who has made all the mistakes that can be made
> in a very narrow field.? - Niels Bohr (1885-1962)
> --
>
> _______________________________________________
> Gretl-users mailing list
> Gretl-users(a)lists.wfu.edu
> http://lists.wfu.edu/mailman/listinfo/gretl-users
> -------------- next part --------------
> An HTML attachment was scrubbed...
> URL:
> http://lists.wfu.edu/pipermail/gretl-users/attachments/20110502/64cd5a06/...
>
> ------------------------------
>
> Message: 7
> Date: Mon, 02 May 2011 12:01:54 +0200
> From: Ignacio Diaz-Emparanza <ignacio.diaz-emparanza(a)ehu.es>
> Subject: Re: [Gretl-users] scatter plot with non-binary factor
> separation
> To: Gretl list <gretl-users(a)lists.wfu.edu>
> Message-ID: <4DBE8112.40504(a)ehu.es>
> Content-Type: text/plain; charset=windows-1250; format=flowed
>
> El 29/04/11 20:37, Allin Cottrell escribi?:
> >
> > 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
>
> Cod_prov is a variable with three integer values, that I marked as
> discrete in the "attributes" dialog. I must say I am obtaining this
> error when I work with a dataset formed by 431 variables. I prepared a
> dataset with only this three variables for sending to this list, but I
> surprisingly found that the command works OK for this small dataset.
> PIB08 and pob08 are variables with rather "normal" values and without
> any missing.
>
> By other side, I had no problem with the new "factorized boxplot"
> although using the large dataset.
>
>
>
>
>
> --
> Ignacio Diaz-Emparanza
> DEPARTAMENTO DE ECONOM?A APLICADA III (ECONOMETR?A Y ESTAD?STICA)
> UPV/EHU Avda. Lehendakari Aguirre, 83 | 48015 BILBAO
> T.: +34 946013732 | F.: +34 946013754
> www.ea3.ehu.es
>
>
>
>
>
>
> ------------------------------
>
> _______________________________________________
> Gretl-users mailing list
> Gretl-users(a)lists.wfu.edu
> http://lists.wfu.edu/mailman/listinfo/gretl-users
>
> End of Gretl-users Digest, Vol 52, Issue 2
> ******************************************
>
13 years
- 1
- 0
Re: [Gretl-users] Johansen question
by Allin Cottrell
On Sun, 1 May 2011, MICHAEL BOLDIN wrote:
> (this post might be considered a test of whether an econometric
> methodology list connected to GRETL would be worthwhile or fills a
> need).
That's an interesting question. Participants in the gretl-users
list are generally tolerant (up to a point) of questions that are
not really gretl-specific. But general questions of econometric
methodology don't fall within the currently advertised purpose of
this list.
I wouldn't mind setting up a parallel list for methodological
questions (as you say, "connected to gretl") if people think (a)
that would be useful, and (b) it's better not to use gretl-users
for this purpose. (If there were another list to which we could
refer methodological queries we could just do so, but so far as I
know there isn't really such a thing.)
Thoughts? (And if positive, suggestions for a name for the list?)
Allin Cottrell
13 years
- 5
- 4