Am 09.01.2011 00:07, schrieb Sven Schreiber:
> Am 08.01.2011 18:20, schrieb Leon Unger:
>> Hi there,
>>
>> I've got a question concering the MacKinnon, Haug, and Michelis (1999)
>> critical values in VECMs.
>> At University I (have to) work with EViews and after performing a
>> Johansen Cointergrating Test including an I(0) exogenous variable.
>> However, I wonder whether the test is biased towards finding a CI vector
>> when including this variable. Hence I looked up in the object reference
>> and found:
>>
>> "Note that the output for cointegration tests displays p-values for the
>> rank test statistics.These p-values are computed using the response
>> surface coefficients as estimated in MacKinnon, Haug, and Michelis
>> (1999). The 0.05 critical values are also based on the response surface
>> coefficients from MacKinnon-Haug-Michelis. Note: the reported critical
>> values assume no exogenous variables other than an intercept and trend."
>>
>> Does anyone know, whether there exist critical values including an I(0)
>> variable different from an intercept and trend?!
>>
> I would look at this article:
>
> @Article{RePEc:eee:econom:v:85:y:1998:i:2:p:339-385,
> author={Byeongseon, Seo},
> title={Statistical inference on cointegration rank in error correction
> models with stationary covariates},
> journal={Journal of Econometrics},
> year=1998,
> volume={85},
> number={2},
> pages={339-385},
> month={August},
> keywords={},
> abstract={No abstract is available for
> this item.},
> url={http://ideas.repec.org/a/eee/econom/v85y1998i2p339-385.html}
> }
>
> It's been a while since I read that paper, so I don't remember the
> concrete solution/answer to your question. I doubt that it was a trivial
> thing, however.
>
> good luck,
> sven
>
Hi there,thanks for this articel! It's indeed far from being trivial and I then sticked to the 'classical' CI analysis without addional stationary covariates. However, 'over' Seo I found another paper by Boswijk and Doornik (2005) that provides a way to approximate the distribution in each case. Interesting stuff, but at least at the moment to complex for me ;-) I attached it to this mail. Have a nice weekend Pindar
Am 09.01.2011 00:07, schrieb Sven Schreiber:
Hi there,Am 08.01.2011 18:20, schrieb Leon Unger:Hi there, I've got a question concering the MacKinnon, Haug, and Michelis (1999) critical values in VECMs. At University I (have to) work with EViews and after performing a Johansen Cointergrating Test including an I(0) exogenous variable. However, I wonder whether the test is biased towards finding a CI vector when including this variable. Hence I looked up in the object reference and found: "Note that the output for cointegration tests displays p-values for the rank test statistics.These p-values are computed using the response surface coefficients as estimated in MacKinnon, Haug, and Michelis (1999). The 0.05 critical values are also based on the response surface coefficients from MacKinnon-Haug-Michelis. Note: the reported critical values assume no exogenous variables other than an intercept and trend." Does anyone know, whether there exist critical values including an I(0) variable different from an intercept and trend?! thanks for this articel! It's indeed far from being trivial and I then sticked to the 'classical' CI analysis without addional stationary covariates. However, 'over' Seo I found another paper by Boswijk and Doornik (2005) that provides a way to approximate the distribution in each case. Interesting stuff, but at least at the moment to complex for me ;-) I attached it to this mail. Have a nice weekend Pindar |
BoswijkDoornikJAE2005Cointegrationtestwithstationaryexogenousregressors.pdf
Description: Adobe PDF document
