Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: RE: Noconst in cointegration relationship in VECM


From   Nick Cox <n.j.cox@durham.ac.uk>
To   "'statalist@hsphsun2.harvard.edu'" <statalist@hsphsun2.harvard.edu>
Subject   st: RE: Noconst in cointegration relationship in VECM
Date   Thu, 28 Apr 2011 14:49:51 +0100

I don't know how to do what you want, but I don't see that it makes much sense anyway. 

If I am misunderstanding, naturally feel free to correct me, but this is my analysis. 
I am regarding -vec- as just a fancy regression, but that could be very wrong. 

The names of your variables indicate that they are all natural logs of something else. 

If you want to force a relationship through the origin, that implies, as I understand it, forcing it through lnprice = lnrent = lnAM = 0 which in turn implies that there is some white magic about the point with three coordinates 

Price = 1 (in whatever units price is measured)

Rent = 1 (ditto)

AM = 1 (ditto) 

-- which seems an almighty strong assumption, and privileges the units of measuring you are using, which normally is just a matter of convention. 

Otherwise put, there can be some definite rationale about forcing through an origin (0, 0) which is, in original coordinates, a limiting case which should be approached, e.g. tiny animals can be expected to converge on some point like 

Weight = 0, length = 0

But why should this be true on logarithmic scales? 

Nick 
n.j.cox@durham.ac.uk 

Svein Olav Krakstad

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.

Could you please help me to figure this out?

*
*   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index