Re: RE: st: RE: constraints insufficient for unique estimate

[Richard Williams <Richard.A.Williams.5@ND.edu>]

At 11:07 PM 8/10/2005 -0500, Zeynal Karaca wrote:
> gen x1x2=x1 x2 and then replace x1 and x2 with the new x1x2
> and the regression. Is it okey or is it meaningful to add
> two dummy variable of the same group? I know that it is fine
> if they are not dummy variables.
>
> if the asnwer to this question is pozitive, then I have
> already solved my problem. if not, please advise me...
>
> Thanks for everybody who spent their valuable time  to
> help me figuring out the problem...
Adding 2 variables together has the same effect as constraining their 
coefficients to be equal.  I am not sure why this would solve all your 
problems (in fact I'd be rather surprised if it did) but if that really is 
all you need, then great.

Incidentally, if you want to use linear constraints but the command does 
not support constraints, then Jeroen Weesie's -linest- command is often the 
next best thing. Also, something like

test x1=x2, coef

will often give you what you want.

-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
FAX:    (574)288-4373
HOME:   (574)289-5227
EMAIL:  Richard.A.Williams.5@ND.Edu
WWW (personal):    http://www.nd.edu/~rwilliam
WWW (department):    http://www.nd.edu/~soc

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/