Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: conditional marginal effects after the Heckman two-step sample selection model in STATA 11


From   "Norbert Wilson" <WILSONL@auburn.edu>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: conditional marginal effects after the Heckman two-step sample selection model in STATA 11
Date   Wed, 29 Dec 2010 12:32:12 -0600

Dear Sir or Madam,

In trying to calculate the marginal effects in the context of the
Heckman two-step sample selection model, I am not clear on the new
procedure in STATA 11.  In STATA 10, "mfx, predict (ycond) varlist (x)"
would produce the marginal effects that are different than the
coefficients estimated in the outcome equation.  In STATA 11 "margins,
dydx (x)" I get the same values as the coefficients of the outcome
equation.  The lambdas are statistically significant; however, STATA
does not adjust the marginals to take in account the conditional effect.
  I have tried to add the "predict ycond" option after margins, dydx
(x), but STATA 11 does not recognize this command "margins, dydx (x)
predict (ycond)".   What is a specific command or option to deal with
the conditional marginal effects in the Heckman two-step sample
selection model?

Thank you,
Norbert

Norbert L. W. Wilson, Ph.D.
Auburn University
Department of Agricultural Economics and Rural Sociology
100 C Comer Hall
Auburn University, AL  36849

(o) 1 334 844 5616
(f)  1 334 844 3519

WilsonL@auburn.edu

Attachment: Norbert Wilson.vcf
Description: Binary data



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index