Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Nick Cox <n.j.cox@durham.ac.uk> |
To | "'statalist@hsphsun2.harvard.edu'" <statalist@hsphsun2.harvard.edu> |
Subject | RE: st: documentation on iteration for a non linear regression |
Date | Wed, 13 Jun 2012 15:50:53 +0100 |
It all depends on what command you are using. You don't say what command you used previously (another piece of advice being ignored), but after -nl- (for example) common steps would be mat b = e(b) di b[1,1] di b[1,2] scalar b1 = b[1,1] scalar b2 = b[1,2] Nick n.j.cox@durham.ac.uk tashi lama Sorry, I read and reread the manual. I am confused. The manual says _b[varname] and _se[varname] to access the coeff and standard error of a var and _b[_cons] and _se[_cons] to access the coeff and standard error of a constant. I am fitting a exponential model y=b1*b2^x to my dataset and got e(b) as mat li e(b) e(b)[1,2] b1: b2: _cons _cons y1 632.7252 .33046311 di _b[_cons] gave me the coeffiecient i.e. 632.73. In the same spirit, I would assume I do di _b[x] to get the coeff of x. There is an error which reads [x] not found. Any idea? * * 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/