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

# RE: st: RE: Noconst in cointegration relationship in VECM

 From DE SOUZA Eric <[email protected]> To "[email protected]" <[email protected]> Subject RE: st: RE: Noconst in cointegration relationship in VECM Date Thu, 28 Apr 2011 19:06:36 +0200

```I realise what you mean now. What Stata does, following the work of Soeren Johansen is to decompose the constant term into two parts. One part makes the equilibrium error equal to zero on average -- this is the constant in the cointegration relation --; the other is what is left over and appears as the constant in the vecm

For this reason you cannot set the constant in the cointegration relation equal to zero. What you have there is the result of a decomposition, which is why no standard errror, etc., is produced for it.

Eric de Souza
College of Europe
Brugge (Bruges), Belgium
http://www.coleurope.eu

-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of Svein Olav Krakstad
Sent: 28 April 2011 16:21
To: [email protected]
Subject: Re: st: RE: Noconst in cointegration relationship in VECM

It seems that i was not able to be write what i mean clear enough.

My question is almost the same as:
http://www.stata.com/statalist/archive/2011-04/msg00351.html

constraint 1 [_ce1]ln_ne = -1
constraint 2 [_ce1]ln_se =  1
vec ln_ne ln_se, bconstrainsts(1/2)

But what I want (which is different) is that I want the constant to be zero (i.e. dropped in the cointegrating vector).

Below i have copied in my table, where I am saying that lnprice is zero in the cointegrating vector, but I want the constant to be zero.

beta |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------
-------------+------
_ce1         |
lnprice |  (omitted)
lnrent |   2.505605   .8862366     2.83   0.005     .7686126    4.242596
lnAM |  -2.238693   .9118165    -2.46   0.014    -4.025821   -.4515656
_cons |  -2.000826          .        .       .            .           .

Is that possible?

Best regards,
Svein Olav

2011/4/28 DE SOUZA Eric <[email protected]>:
> It is not clear to me which case you want:
>  trend(constant) include an unrestricted constant in model; the
> default
>  trend(rconstant) include a restricted constant in model
>  trend(trend) include a linear trend in the cointegrating equations
> and a quadratic trend in the undifferenced data
>  trend(rtrend) include a restricted trend in model
>  trend(none) do not include a trend or a constant See page 477 of the
> time series manual for a detailed explanation
>
>
> Eric de Souza
> College of Europe
> Brugge (Bruges), Belgium
> http://www.coleurope.eu
>
>
> -----Original Message-----
> From: [email protected]
> [mailto:[email protected]] On Behalf Of Svein Olav
> Sent: 28 April 2011 15:27
> To: [email protected]
> Subject: st: Noconst in cointegration relationship in VECM
>
> Hi,
>
> I am trying to have no constant in the cointegration vector in the VEC model.
>
> I know how to have constraints on the variables, but the constant does not work in the same way. For example if I restrict (i.e.) the variable lnrent:
>
> constraint define 1 [_ce1]lnrent=1
>
> vec lnprice lnrent lnAM, rank(1) lags(2) trend(constant)
> bconstraints(1)
>
> It works fine.
>
> Then I am thinking that it should only be to restrict the constant in the same way:
>
> constraint define 1 [_ce1]_cons=0
>
> vec lnprice lnrent lnAM, rank(1) lags(2) trend(constant)
> bconstraints(1)
>
> But this do not work.
>
> *
> *   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/

*
*   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/
```