[Gretl-users] Cointegration Engle-Granger ?

[Allin Cottrell]

On Tue, 25 Jul 2006, Sven Schreiber wrote:

> Allin Cottrell schrieb:
>>
>> But I now think, from re-reading MacKinnon (1996), that the 
>> relevant factor here is not the setup of the DF regression 
>> for the residuals, but whether or not the cointegrating 
>> regression itself includes a constant.
>
> My guru-ness is limited, but just about sufficient to confirm that...

Thanks.

> Btw, what about the case with a deterministic trend? Is that 
> covered by gretl? Should it be?

It's not covered at present, for Engle-Granger (though it is in 
the Johansen test).  Yes, it should be there for completeness.

Allin.