re: st: ...non parametric alternative to ANOVA...

[David Airey <david.airey@vanderbilt.edu>]

Lawrence Hamilton shows how to use robust regression in Stata to do 
robust analysis of variance for a two way ANOVA using rreg or qreg 
(page 203-208, Statistics with Stata v7). In that case, the interaction 
can be estimated. Assuming the ANOVA is a simple two way ANOVA with 
both effects fixed, this is an interesting solution. Doesn't Friedman's 
ANOVA concern one fixed and one nuisance (random) variable, as in a 
simple one factor repeated measures design (treatment, subject)?

-Dave

*
*   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/