Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.

# Re: st: RE: VEC: Missing Output Data

 From Barbara Engels To statalist@hsphsun2.harvard.edu Subject Re: st: RE: VEC: Missing Output Data Date Thu, 7 Jul 2011 14:33:39 +0200

```Thanks a lot, that clarifies things significantly.
El 07.07.2011, a las 13:48, DE SOUZA Eric escribió:

> I thought you were referring to this, which is why I added the "keep in mind" to my reply
> Dy = A0 + P1.Dy(t-1) + P.y(t-1)  = A0 + P1.Dy(t-1) + A.B.y(t-1)
> B is not identified, meaning that P = A*.B* = (A*G).(Ginverse.B*) = A**.B**
> P can be decomposed into an infinite number of A's and B's
>
> One identification rule is to set B = [I B2] where I is the unit matrix
> Since I is set it is not estimated and, therefore, has no standard errors and the like.
>
> In your output extract below, the column Coef is giving you the first row of B: 1 0 0 0 -.046 .013
> The e-15's  and e-17's are just zeroes.
>
>
> Eric de Souza
> College of Europe
> Brugge (Bruges), Belgium
> http://www.coleurope.eu
>
>
>
> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Barbara Engels
> Sent: 07 July 2011 13:35
> To: statalist@hsphsun2.harvard.edu
> Subject: Re: st: RE: VEC: Missing Output Data
>
> The problem I see is for example in this output:
>
>> Identification:  beta is exactly identified
>>                Johansen normalization restrictions imposed
>> ------------------------------------------------------------------------------
>>       beta |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
>> -------------+----------------------------------------------------------------
>> _ce1         |
>>     tfp_in |          1          .        .       .            .           .
>>      lnbrd |   6.25e-17          .        .       .            .           .
>>      lnfrd |   5.55e-17          .        .       .            .           .
>> lllneduexp |  -3.33e-16          .        .       .            .           .
>>     llnftl |  -.0461967   .0200468    -2.30   0.021    -.0854877   -.0069057
>>   impshare |   .0132646   .0020457     6.48   0.000     .0092551    .0172741
>>      _cons |  -.3241717          .        .       .            .           .
>
>
>
> Why is there no Std. Err. etc. for lnbrd, lnfrd, ... ?
> And still, I don't really know how I could make an ECM out of the VEC results.
> Barbara
>
>
>
>
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
>
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/
```