st: Fw: Re: Marginal effects for Heckman model

[Maarten buis <maartenbuis@yahoo.co.uk>]

Lenka Vavroušková had trouble posting the follwing question on statalist:

> Dear statalisters,
> 
> I have question in relation to interpretation of Heckman
> two-step estimation results. As was already mentioned in the
> previous threads the coefficients in the outcome equation
> can be interpreted itself, it is needed to get marginal
> effects.
> 
> How can I estimate marginal effects after Heckman model
> based on the Hoffmann and  Kassouf (2005) article -
> Appendix A. They state that the unconditional marginal 
> effects computed in STATA corresponds to expressions (A.9),
> (A.10), which are exactly the values I would like to
> obtain.
> 
> Will the command: mfx, predict (yexpected) do it for me?
> 
> I will be extremely grateful for any help.
> 
> Lenka Vavrouskova
> Czech University of Life Sciences Prague
> 
> Rodolfo Hoffmann & Ana Lúcia Kassouf, 2005. "Deriving
> conditional and unconditional marginal effects in log
> earnings equations estimated by Heckman's procedure,"
> Applied Economics, Taylor and Francis Journals, vol. 37(11),
> pages 1303-1311
> 
> # ------------ Původní zpráva ------------
> # Od: Lenka Vavroušková <le.v@email.cz>
> # Komu: <statalist@hsphsun2.harvard.edu>,
> # Kopie:
> # Předmět: marginal effects - Heckman two-step
> estimation
> # Datum: 19.11.2010 13:39:55
> # ----------------------------------------
> # Dear statalisters,
> #
> # I have question in relation to interpretation of Heckman
> two-step estimation
> # results. As was already mentioned in the previous threads
> the coefficients in
> # the outcome equation can be interpreted itself, it is
> needed to get marginal
> # effects.
> #
> # How can I estimate marginal effects in STATA 10 based on
> the Hoffmann and
> # Kassouf (2005) article - Appendix A. They state that the
> unconditional marginal
> # effects computed in STATA corresponds to expressions
> (A.9), (A.10),
> # which are exactly the values I would like to obtain.
> #
> # Will the command: mfx, predict (yexpected) do it for me?
> #
> # I will be extremely grateful for any help.
> #
> # Lenka Vavrouskova
> # Czech University of Life Sciences Prague
> #
> # Rodolfo Hoffmann & Ana Lúcia Kassouf, 2005.
> "Deriving conditional and
> # unconditional marginal effects in log earnings equations
> estimated by Heckman's
> # procedure," Applied Economics, Taylor and Francis
> Journals, vol. 37(11), pages
> # 1303-1311
> #
> 


      

*
*   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/