Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: bootstrapping two-part model and svy


From   Stas Kolenikov <skolenik@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: bootstrapping two-part model and svy
Date   Sat, 18 Sep 2010 00:01:33 -0500

I hate to self-advertise, but you might want to take a look at
http://stata-journal.com/article.html?article=st0187 -- you just need
to bootstrap your two-part-code appropriately. It would need to
support [pw], for instance. I am usually terrified by -drop- and
-replace- statements, especially within programs. You might want to
use -tempvar-s to avoid this sort of destructive behavior. But that's
just a style issue.

On Fri, Sep 17, 2010 at 10:20 PM, Sarah Beth Link <sblink7@gmail.com> wrote:
> I am using a two-part model in stata 10.  The first part of the model
> is a logit that predicts the probability of a positive outcome and the
> second part of the model is a GLM estimated only on observations with
> positive outcomes (in this case expenditures).  The final outcome I am
> interested in is the average treatment effect of a dummy variable.  I
> would like to bootstrap the entire program to get the 95% confidence
> interval on the average treatment effect.

-- 
Stas Kolenikov, also found at http://stas.kolenikov.name
Small print: I use this email account for mailing lists only.

*
*   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/


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