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 at the end of May, and its replacement, is already up and running.

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

Re: st: Nonlinear constraints in -ml- programming

From   Muyang Zhang <>
Subject   Re: st: Nonlinear constraints in -ml- programming
Date   Sun, 17 Feb 2013 10:06:09 +0800

Maybe I have used a incorrect notation. I didn't mean to have N
dummies with N observations. The number of observations is larger than
the number of dummies.

The FAQ you shared discussed the way to deal with interval
constraints, but my problem is a "proportional constraints" where the
coefficient of the 2nd equation over the coefficient of the 1st
equation is constant for all dummies.

On Sat, Feb 16, 2013 at 10:34 PM, Maarten Buis <> wrote:
> On Sat, Feb 16, 2013 at 1:17 PM, Muyang Zhang wrote:
>> I wish to estimate a SUR model with nonlinear constraints. The model is like:
>> y_1=x_1 beta_1+d_j delta_j (j=1..N)
>> y_2=z_1 gamma_1 +d_j eta_j (j=1...N)
>> and I require delta_j/eta_j is constant over all j's, so this is not a
>> linear constraint.
>> How can I add nonlinear constraints in -ml- programming?
> That is discussed here:
> However, I suspect that your model contains way too many parameters to
> lead to a stable fit.
> Hope this helps,
> Maarten
> ---------------------------------
> Maarten L. Buis
> Reichpietschufer 50
> 10785 Berlin
> Germany
> ---------------------------------
> *
> *   For searches and help try:
> *
> *
> *

Muyang Zhang
Ph. D. Candidate
China Center for Economic Research
Peking University
Beijing, 100871
*   For searches and help try:

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