Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Garret Christensen <garretchristensen@yahoo.com> |
To | Stata List <statalist@hsphsun2.harvard.edu> |
Subject | st: Testing coefficients across different models |
Date | Fri, 10 Sep 2010 22:13:06 -0700 (PDT) |
Statalisters, I'd like to test whether coefficients change across models. The Stata FAQ addresses this in for simple models (http://www.stata.com/support/faqs/stat/testing.html), but I'm confused about slightly more complicated circumstances. My original command/model is reg y x1 x2 z x3 x4 Then I change some observations in z, and I'd like to test if the coefficients on x1 and x2 are the same as before. I don't care about the coefficients on x3 or x4 (they're fixed effects). Based on the help at the FAQ above, here's what I'm doing: use originaldata gen disturbed=0 reg y x1 x2 z x3 x4 save originaldata, replace replace z=z+[some disturbance] reg y x1 x2 z x3 x4 gen disturbed=1 append using originaldata gen dx1=disturbed*x1 gen dx2=disturbed*x2 reg y x1 x2 z x3 x4 disturbed dx1 dx2 Is that the right set-up? I expected the coefficients on disturbed, dx1 and dx2 to be close to zero, but they aren't. Do I have to include interactions for x3 and x4? (That might be a hassle since I've got a lot of fixed effects.) When I get this set up correctly, to test separately whether x1 or x2 are different: test _b[disturbed]=0, notest test _b[x1]=0, accum and then test _b[disturbed]=0, notest test _b[x2]=0, accum thanks, Garret Christensen * * 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/