st: RE: Testing equality of coefficients using ivregress between a baseline and an expanded model

["Schaffer, Mark E" <M.E.Schaffer@hw.ac.uk>]

Eric,

> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu 
> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of 
> Eric Sjöberg
> Sent: 15 March 2011 09:53
> To: statalist@hsphsun2.harvard.edu
> Subject: st: Testing equality of coefficients using ivregress 
> between a baseline and an expanded model
> 
> Dear statalisters,
> 
> I am estimating two regressions using IV
> 
> ivregress 2sls y (x1 = z1), vce(cluster id)
> ivregress 2sls y (x1 = z1) x2, vce(cluster id)
> 
> I want to test whether the coefficient belonging to x1 is
> statistically different in the two models. Storing the estimates and
> using suest cannot be done since ivregress is not compatible with
> suest. I read a thread on a related topic where the user wanted to
> compare coefficients of the same IVregression but in different
> subsamples but I don't see how this method is applicable in my case.
> 
> http://statalist.1588530.n2.nabble.com/test-of-the-equality-of
> -coefficients-in-two-models-td5427850.html

Stacking still works.  You just need to remove the "common coefficients" restriction by interacting the regressors with a dummy defining the equation.  The effect is to make your matrix of your regressors block-diagonal.

--Mark

> I don't know if this matter but the x2 is not a single variable but
> rather an additional vector of controls. Any suggestions on how to do
> this are most welcome!
> 
> Best
> --
> Eric Sjöberg
> 
> *
> *   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/
> 


-- 
Heriot-Watt University is a Scottish charity
registered under charity number SC000278.


*
*   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/