[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: RE: re: nonlinear constrained estimation and "makecns"

From   Maarten buis <>
Subject   Re: st: RE: re: nonlinear constrained estimation and "makecns"
Date   Mon, 28 Apr 2008 15:47:12 +0100 (BST)

--- Francesco Mariotti <> wrote:
> Y1=X1*b1+X2*b2+X3*b3
> Y2=X1*t1+X2*t2+X3*t3
> where X1 X2 and X3 are the same in both equations. I have to estimate
> these two imposing the restriction t1/b1=t2/b2. I have the additional
> issue that X3 (I have several variables in X3, so I was just using a
> more compact form) is potentially correlated with the errors. How can
> I tackle the whole thing imposing the restrictions and without having
> to specify other equations for the endogenous variables in X3? 

You don't. Even if these kinds of short cuts exist, they inevitably
lead to disaster. I don't think there is an easy solution to your
problem. In your case I would specify the entire model, derive the
log-likelihood, and maximize this using -ml-. As I remarked earlier
this problem is similar, but as Kit remarked not the same, as
-propcnsreg-. While programming -propcnsreg- I noticed that the
likelihood is rather nasty, with local maxima. So you'll probably want
to invest some aditional time in getting good starting values. Anyhow,
this would be a major project. 


Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands

visiting address:
Buitenveldertselaan 3 (Metropolitan), room Z434

+31 20 5986715

Sent from Yahoo! Mail.
A Smarter Email
*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index