Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: Calculate Marginal Effect after IVPROBIT


From   "Austin Nichols" <austinnichols@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Calculate Marginal Effect after IVPROBIT
Date   Mon, 9 Jul 2007 11:01:30 -0400

Prabal Kumar De <prabal.de@nyu.edu>:
See
http://www.stata.com/support/faqs/stat/mfx_nose.html
and note -dprobit- uses these formulas to calculate marg fx and SEs:

Indicator Variables
Dp = F(x2*b) - F(x1*b)
d(Dp)/db = f(x2*b)*x2 - f(x1*b)*x1
Vhat(Dp) = [d(Dp)/db)]' Vhat(b) [d(Dp)/db]
Continuous Variables
p = F(x*b)
dp/dx = f(x*b)*b = g(b)
dg/db = f'(x*b)b'x + f(x*b)I
Vhat(dp/dx) = [dg/db] Vhat(b) [dg/db]'

presumably you could do this "by hand" as well.

On 7/8/07, Prabal Kumar De <prabal.de@nyu.edu> wrote:
Hi!
   I need to know what is the best way to calculate the marginal effect after running IVPROBIT. I use -mfx- , but it is not reporting standard errors ( even after specifying the value at which to be calculated). I could not find something like -divprobit-
Any help will be much appreciated.
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



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