--- On Wed, 18/11/09, [email protected] wrote:
> I am running a non linear Oaxaca decomposition using the
> command "nldecompose" in Stata 10. I would like to
> compute standard errors and I am using the bootstrap
> option for that purpose, but I am getting a different
> number of replications (and slightly different standard
> errors) every time I run the model. I always specify 100
> reps.
This suggests that the underlying non-linear model did not
converge in all of your bootstrap samples. This can, for
example, happen in case of a -logit- when your explanatory
variables perfectly predict an outcome in some bootstrap
samples.
Hope this helps,
Maarten
--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany
http://www.maartenbuis.nl
--------------------------
*
* 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/
