st: Bootstrapping difference in coefficients of same variable between two models

[Kristian Karlson <kristian.karlson@gmail.com>]

Hi,

I need to compare regression coefficients of the same variable between 
two models with different control variables:

reg y x
reg y x z

I am intersted in the _difference_ between the effects of x in the two 
models. I wan't to bootstrap the difference in order to obtain the 
standard error of the difference. (I am aware of the Clogg et al. 
AJS-1995 analytical solution for the standard error, but I need to do 
the bootstrap as well).

However, I have browsed through the -bootstrap- help file and Statalist, 
but I can't figure out how to do it, when the bootstrapping involves two 
commands.

All the best,
Kristian

*
*   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/