I found an earlier conversation on this, and I used a variant of Yatchew's method of first differencing with locpoly to run a partially linear model. 
Now I'd like to get some confidence intervals, but all I can find is instructions to bootstrap them. I have not been able to figure out how to use locpoly with the bootstrap command. Any hints?
Thanks,
Sharon
      
*
*   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/