Stepwise regression is generally a bad idea:
http://www.stata.com/support/faqs/stat/stepwise.html
That said, it can be a useful tool on occasion, if only to satisfy
public demand - which is why I wrote some programs which perform a limited
(ie, backwards only, LR criteria only) stepwise regression for xtmixed
& xtlogit. I'd be happy to share them, though not to document them.
cheers,
Jeph
*
* 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/
