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.

# st: Re: creating constraints in panel data

 From Kit Baum To statalist@hsphsun2.harvard.edu Subject st: Re: creating constraints in panel data Date Fri, 5 Mar 2010 07:52:34 -0500

```<>
On Mar 5, 2010, at 2:33 AM, Valeriano wrote:

> The way I understand your answer, I must regress a new equation (lnY - lnX3) = a (lnX1-lnX3) + b(lnX2-lnX3)+...., which I presume is the same as ln(Y/X3)= a ln(X1/X3) + b ln(X2/X3)+....
> And after this regression I use the command "lincom", but I do not understand well the syntax of the lincom command.
>

That is the correct regression, upon which you have imposed the constraint a + b + c = 1, therefore c = 1 - a - b

if you
regress yx3 x1x3 x2x3   (naming the transformed variables in that manner) then

lincom 1 - x1x3 - x2x3

will compute a point and interval estimate of c.

You might find an econometrics book such as Wooldridge, Introductory Econometrics, useful.

Kit Baum   |   Boston College Economics & DIW Berlin   |   http://ideas.repec.org/e/pba1.html
An Introduction to Stata Programming  |   http://www.stata-press.com/books/isp.html
An Introduction to Modern Econometrics Using Stata  |   http://www.stata-press.com/books/imeus.html

*
*   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/
```