st: replicability of bootstrap standard errors in quantile regression

[Jessica Goldberg <jegoldbe@umich.edu>]

I am having trouble reproducing bootstrap standard errors, despite 
setting the seed immediately before the regression command.  If I run 
the same .do file twice, I get different standard errors each time.

However, if I repeat the code within the same .do file (re setting the 
seed), I get the same standard errors within the file.

The lines of code I am using are:

set seed 123456789
bsqreg earnwke sex age age2 ed_9to10-ed_16ormore, q(.5) reps(50)

I've had the same results setting the seed in the same line as running 
the regression.

I'd appreciate any suggestions.  Thank you for your help.

Jessica Goldberg
jegoldbe@umich.edu
PhD student, Department of Economics
University of Michigan

*
*   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/