Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: bootstrapping over multiple commands


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: RE: bootstrapping over multiple commands
Date   Tue, 17 May 2005 20:44:41 +0100

I think the answer is Yes and No and both 
are correct. 

The syntax for -bootstrap- makes it clear
that it is a framework for repeatedly 
running a single command. 

However, there is nothing to stop 
you putting a sequence of commands in 
a single program. To Stata that is then 
just another command. The key is that the 
results must be visible to -bootstrap-. 
(At a guess, this would work with 
a do file too, with the same caveat.) 

Nick 
n.j.cox@durham.ac.uk 

Scott Imberman
 
> I would like to know if there is any way to bootstrap over multiple
> commands in Stata9.  In particular i'm trying to bootstrap 
> over matching
> estimators using psmatch2.  However, I have too many variables in my
> propenstity score for psmatch2 to use directly and i need to 
> weight the
> propensity scores which cannot be done in psmatch2.  Thus, to get my
> bootstrap standard errors i need to bootstrap over a probit command, a
> prediction of the propensity score, and then psmatch2.  I'd greatly
> appreciate any help you can give.

*
*   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