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, is already up and running.

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

Re: st: unequal constraints

From   Maarten buis <>
Subject   Re: st: unequal constraints
Date   Wed, 14 Jul 2010 02:49:59 -0700 (PDT)

--- On Wed, 14/7/10, Sirak wrote:
> In estimating an econometric cost function and associated share
> equations (using Stata 10.1), I have tried to estimate an equation
> with constraints that three of the parameters sum to one. While these
> constraints held when estimating the equations for the cost function
> with the -sureg- command, the estimates of the parameters (input
> shares) took on values less than zero and greater than one, which are
> not possible in practice.
> I tried to define inequality constraints like this.
> eg. constraint 1 _b[y3x1] = 1 - _b[y2:x1] - _b[y1:x1],
>    sureg (y1 x1 x2 x3)    ///
>      (y2 x1 x2)              ///
>      (y3 x1 x2), constraints (1)         ///
> the constraint 1 _b[y3x1] = 1 - _b[y2:x1] - _b[y1:x1], this is to get
> the sum of input shares is equal to one.
> What about if I want to make constraints for the coefficients to be
> greater than one. In other ways how do I make inequality constraints
> in regeression???

I answered that same question yesterday:

Bottom line: if you want to do that you'll need to some
programming. I personally would not consider it worth the
effort if it were just for one time use. On the other hand 
there is apperently some demand for it, so it may be a 
project someone wants to pick up to create a program that 
estimates that particular model and submit it to SSC.

Hope this helps,

Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen


*   For searches and help try:

© Copyright 1996–2016 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index