st: Marginal effects and standard errors after ivprobit twostep

[aslihan arslan <aslihanarslan@yahoo.com>]

Hi statalisters,
I have read old posts of the statalist on how to obtain the marginal effects after ivprobit twostep:
http://www.stata.com/statalist/archive/2007-01/msg00975.html
http://www.stata.com/statalist/archive/2008-05/msg00199.html

I have read the referred sections in Wooldridge's book, but I am not sure whether I understand it correctly.  He says:
" Divide each coefficient by Sqrt[(Cov(v2,u1)^2/Var(v2)) + 1]  BEFORE computing derivatives or differences (where v2 and u1 are the error terms of 1st and 2nd steps, resp.).  He also says obtaining standard errors of APE would be very difficult.

I was wondering whether I can get clarification on 2 points:
1) I am not sure whether we just divide the coeffs by this factor to
get the marginal effects, or there is some other step after this I do
not understand. Would someone please let me know how to obtain the
marg. effects?

2) Is there a way to obtain the standard errors of the APE after ivprobit twostep?

Any help will be greatly appreciated!
Best,
Aslihan Arslan


      
*
*   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/