The Johansen trace and maximum eigenvalue statistics both have the same null. (Rank(Pi)=r) but different alternatives.  The alternative for the trace test is
Rank(Pi) > r
The alternative for the maximum eigenvalue test is rank(Pi)  = r+1.

On 26/10/06, javier garcia enriquez <> wrote:
At this moment we are doing a cointegration analysis and a doubt has come up about the nule hypothesis that your programme uses in the Johansen test.We don´t know if the maximum eigenvalue uses the same nule hypothesis as the trace contrast( as for instance, Eviews does) , I mean, if both of them contrast the hypothesis that there are, at most, "r" cointegration vectors or, on the contrary, as we have read in some papers, this is only done by the trace one, while the maximum eigenvalue contrasts that there are exactly "r" cointegration vectors.
What we want to know exactly is if in your programme both of them use the same nule hypothesis ( at most "r" cointegration vectors) or the trace one uses that one, while the maximum eigenvalue uses the other one ( exactly "r" cointegration vectors).
Seeing the results we have got, we think that both of them use the same one cause, if it isn´t like that, the contrast of the maximum eigenvalue would say it exists 0 and 1 cointegration vectors at the same time.  

LLama Gratis a cualquier PC del Mundo.
Llamadas a fijos y móviles desde 1 céntimo por minuto.

Gretl-users mailing list

John C Frain
Trinity College Dublin
Dublin 2