Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Giannis Paraskeuopouls <gparaskeuopouls@hotmail.gr> |
To | <statalist@hsphsun2.harvard.edu> |
Subject | st: SE AND CI FOR OF COMBINATIONS OF MARGINAL EFFECTS |
Date | Wed, 11 Aug 2010 19:58:18 +0100 |
<> Dear all, I want to run 3 separate models. Indeed, reg y x1 x2 x3 x4 x5 x6 [model y] mlogit x2 x3 ..... [model x2] probit x4 x3 ... [model x4] Then I am interesting in calculating non-linear combinations of the parameters of the different models. To be more precise, I would like to calculate combinations of the marginal effects (from the coefficients of the mlogit models) and the OLS coefficients. Something like: [y]_b[x4]*[x4]_marginaleffect(x3). I try to use -suest command after the estimation of the 3 models. This is a good idea because it is doing what I want (I can do non-linear combinations from the different models), however, due to the fact that I am interesting in the marginal effects of the last models, -suest fails to save marginal effects from these models. Of course, I can calculate the combinations by hand (by multiplying the co-efficient from the different models) but I cannot take SE or CI. I really appreciate your help. * * 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/