ricardo,
a user-written program, -kwallis2-, may get you where you want to go...
--clint
>
> Dear all,
>
> I use the nonparametric -kwallis- test and obtain
> these significant results:
>
> . kwallis outcome ,by(group)
>
> Test: Equality of populations (Kruskal-Wallis test)
>
> +---------------------------+
> | group | Obs | Rank Sum |
> |----------+-----+----------|
> | Placebo | 12 | 278.00 |
> | Drug 1 | 12 | 265.00 |
> | Drug 2 | 12 | 170.00 |
> | Drug 3 | 12 | 107.00 |
> +---------------------------+
>
> chi-squared = 14.457 with 3 d.f.
> probability = 0.0023
>
> chi-squared with ties = 14.457 with 3 d.f.
> probability = 0.0023
>
>
> Is there a way to test which drug groups differ while
> maintaining the correct type I errror? Maybe,
> something similar to Duncan's test after Anova, or
> multiple adjustment method.
>
> Thank you,
> Ricardo.
>
> Ricardo Ovaldia, MS
> Statistician
> Oklahoma City, OK
>
> __________________________________________________
> Do You Yahoo!?
> Tired of spam? Yahoo! Mail has the best spam protection around
> http://mail.yahoo.com
> *
> * 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/
>
*
* 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/
