st: nonlinear LS and robust

[Kit Baum <baum@bc.edu>]

Larry Chavis couldn't get _robust to work after nl. The trick is 
'leave':

webuse klein,clear
nl log4 consump totinc, leave
tempvar e
mat b = e(b)
mat D= e(V)
predict double `e' if e(sample),r
_robust `e' if e(sample), v(D)
ereturn post b D, depn(`e(depvar)')
ereturn display

without the 'leave' option, _robust can't find the "variable" named b0.

Kit

*
*   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/