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

Re: st: Bootstrap marginal effects for two-step IV

From   "Austin Nichols" <>
Subject   Re: st: Bootstrap marginal effects for two-step IV
Date   Thu, 26 Jul 2007 15:37:53 -0400

You cannot try my example exactly on your own data, since the data are
part of the example. The example runs fine (as shown) on my
computer--whether it does what you want or not is up to you to decide,
and whether it can be modified to fit your data, are in any case both
separate issues.  On the second issue, you may want to run the program
once on the full sample:
eret li
mat li e(Xmfx_dydx)
mat li b
and so forth to see what output is being picked up by -bootstrap-.

My example should not be construed as indicating that I endorse the
use of -mfx- after -logit- or -glm- (I think predictions over the
whole sample, replacing values as appropriate to generate "custom"
marginal effects, are more informative).

The Reference A-H manual has a good entry on -bootstrap- beginning at page 200.

On 7/26/07, Michael Furukawa <> wrote:
Thanks for the helpful suggestions.

I have tried your program exactly (on my own data) but get the following
error message:
'r(mfx)' evaluated to missing in full sample

Any thoughts on how to fix this?
*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index