>Why not rank your dv? I think I remembered this covered in Neter et
>al., 1996, Applied Linear Models. I don't have it handy to double
>check.
>
>With regard to what Roger said, (wow), why not run his idea and see how
>badly the fit is? You might get away with his solution.
>
>-Dave
I meant to reply to this sooner. My boss is a SAS person and is willing
to accept ranking the dv. The other methods are quite elegant in comparison
but it's like trying to push water up a hill around here. You should see
their faces when they see the graphs Stata can do compared to SAS.
You don't mention it but I believe the next step after ranking is to
then do the anova. Is that correct?
*
* 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/
