Imposing Constraints on a Regression Model Using Stata.

[Abdulaleem Isiaka]

Hello Everyone,

I intend estimating a regression model of the form: log(y) = ax1 + bx2 + cx3 + dx4. Where a, b, c and d are the parameter estimates, x1, x2, x3 and x4 are the explanatory variables and log(y) is the dependent variable. Please, I would like to know if there is a way I could use Stata to estimate this kind of model with the constraint that an aspect of the equation is equal to 1 (e.g. the constraint that ax1 + bx2 = 1)? I would also be happy to study any text you may want to recommend on the subject.

Many thanks.

[Carlo Lazzaro]

Adulaleem:
welcome to this forum.
See -cnsreg- entry in Stata .pdf manual.

[Abdulaleem Isiaka]

Thank you so much for the prompt response Carlo. I find it very helpful.