Johansen
by Javier García
Hi;
Before I put a Gretl's example. Data set which I study is monthly. I have
101 observations and, if I apply the Johansen's tests in it, I obtain
following output:
Rank
Eigenvalue
Trace
p-value
L-máx
p-value
0
0,11637
13,736
[0,3151]
11,01
[0,2600]
1
0,030163
2,7258
[0,6392]
2,7258
[0,6380]
Then I question to my self: if two hypothesis are accepted, why we must
conclude that there aren't any cointegration relationships??? To conclude
that I think we have to interpretate sequently, that is, starting with the
less rank, the first rank we accept it will be the rank of cointegration,
won´t it? In this case rank zero, doesn´t it?
If the null hypothesis in L-max were that there are exactly "r0" ( and no
r<=r0 as the trace test)) cointegration vectors, it would impossible the
interpretation, because the rank would be, at the same time, zero and one.
In a lot of articles there is that distintion between both tests.
I continue thinking that this isn't very clear in Gretl
Cheerssssss and thanksss
Javi
17 years, 3 months
Bug report
by Andreas Karlsson
Hi,
I am using gretl 1.6.0 on windows XP.
A couple of bugs:
1. Create a frequency plot
2. Choose Edit> Lines > Type > Lines (or somthing else in the list)
3. Choose Edit> Lines > Type: Boxes has disappeared from the list anc
cannot be choosen again
For a discrete variabel:
1. Create a frequency plot
2. Choose Edit>Main > Uncheck Show full border > Bars become connected
3. Check Show full border again: nothing changes, bars are still connected
Regards
Andreas
17 years, 3 months
Johansen
by javier garcia enriquez
HI,
And in following sample...What would you say? Are there zero cointegration vectors or one??? So , the tests accept the both hypothesis. I think it's a bit confused...
Johansen's tests
Caso 3: constante no restringida
Rank Eigenvalue Trace p-value Lmáx p-value
0 0,33879 9,1310 [0,3600] 8,6874 [0,3204]
1 0,020900 0,44356 [0,5054] 0,44356 [0,5054]
We will can accept that there are zero cointegration vectors if and only if we suposse a secuencial interpretation, don't we??? First look at the rank zero and, if this is not refused, then look at the rank 1 and...until rank 'k'
Cheers
Javi
---------------------------------
LLama Gratis a cualquier PC del Mundo.
Llamadas a fijos y móviles desde 1 céntimo por minuto.
http://es.voice.yahoo.com
17 years, 3 months
Johansen
by javier garcia enriquez
Hi;
I wanted to know what are the hypothesis that Gretl uses in the Johansens tests (trace and lambda max). We think there is a very confused topic in the literature, because some articles (programs) says(uses) that both have the same hypothesis (H0: r <= r0; H1: r>r0), while others defend the following:
Trace H0: r <= r0 H1: r>r0
Lambda max H0: r =r0 H1: r>r0
Where r0 is the number of coitegration vectors
Is Gretl use either of them??
Thanks
Javi
---------------------------------
LLama Gratis a cualquier PC del Mundo.
Llamadas a fijos y móviles desde 1 céntimo por minuto.
http://es.voice.yahoo.com
17 years, 3 months
Johansen
by javier garcia enriquez
Hi;
I wanted to know what are the hypothesis that Gretl uses in the Johansens tests (trace and lambda max). We think there is a very confused topic in the literature, because some articles (programs) says(uses) that both have the same hypothesis (H0: r ≤ r0; H1: r>r0), while others defend the following:
Trace H0: r ≤ r0 H1: r>r0
Lambda max H0: r =r0 H1: r>r0
Where r0 is the number of coitegration vectors
Is Gretl use either of them??
Thanks
Javi
---------------------------------
LLama Gratis a cualquier PC del Mundo.
Llamadas a fijos y móviles desde 1 céntimo por minuto.
http://es.voice.yahoo.com
17 years, 3 months
gets estimation
by john w
Hi,
once I asked about gets estimation. Now I found something what could be
(maybe) usefull.
And it could be implemented (maybe) in gretl. This code for gets estimation
is already implemented in Grocer (http://dubois.ensae.net/grocer.html) which
is open source!
Taken from Grocer web page:
- a pc-gets like device, that performs automatic general to specific
estimations
- etc.
What do you think? Is it possible?
Thnx
_________________________________________________________________
Think you're a film buff? Play the Movie Mogul quiz and win fantastic
prizes! http://www.msnmoviemogul.com
17 years, 3 months
Re: [Gretl-users] Suggestions for improvements of gretl
by Riccardo (Jack) Lucchetti
On Wed, December 20, 2006 22:25, Riccardo (Jack) Lucchetti wrote:
> x += (uniform()>p)
sorry, that should be
x += (uniform()<p)
Riccardo (Jack) Lucchetti
Dipartimento di Economia
Facoltà di Economia "G. Fuà"
Ancona
17 years, 3 months
gretl interface (2)
by Franck Nadaud
Dear Riccardo, and listers
Thanx again, for the quick response.
Effectively i use mainly the graphical client for now. However, to be
more specific, for a while, gretl used to print output of most (not all)
commands in a single window, thus the results were added along, this is
what i called "continuous scrolling". At the end of a session a single
text filed could be saved with all the results as well as the command log.
Now, with every command from the menus a new window is opened, and gretl
does not save a text file with the results. Maybe it is no longer
possible since 1.6 to have a single scrolling window ?
What puzzles me a bit is that the change took place suddenly, well, i
dont remember exactly if it occured when i updated to 1.6.
salut à tous !
amicalement
--
Franck Nadaud
CIRED
Centre International de Recherche sur l'environnement et le Développement
CNRS EHESS UMR 8568
Campus du Jardin Tropical de Paris
45 bis avenue de la Belle Gabrielle
94736 Nogent sur Marne Cedex
Tél : 01 43 94 73 94 (ligne directe)
FAX : 01 43 94 73 70
17 years, 4 months
adf
by javier garcia enriquez
Thanks, I dindn´t find because I hadn´t the Gretl manual updated
Cheers
Javi
---------------------------------
LLama Gratis a cualquier PC del Mundo.
Llamadas a fijos y móviles desde 1 céntimo por minuto.
http://es.voice.yahoo.com
17 years, 4 months
ADF
by javier garcia enriquez
Hi;
Could you tell me which criterion follows the ADF test to select the size of 'p' automatically? Is the Akaike criterio?
Thanksss
Javi
---------------------------------
LLama Gratis a cualquier PC del Mundo.
Llamadas a fijos y móviles desde 1 céntimo por minuto.
http://es.voice.yahoo.com
17 years, 4 months
