Thanks for your discussion, Daniel and Richard.
Actually I wanted to do a two stage regression (2sls) and then a chow test, but I have a dilemma:
I wanted to do a first stage regression and get the predicted value of x1, and then test if x1 differs across groups. But if I do the first stage regression on the whole sample, then, I'm assuming there's no difference between the two groups; or if I do the first stage regression separately, I'm assuming there's difference between the two groups before even testing it with my chow test.
-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of Richard Williams
Sent: 2005年2月20日 12:33
To: [email protected]
Subject: RE: st: question on chow test
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
