--- "Xu, Kexin" <[email protected]> wrote:
> I find a lot of information about multiple
> comparison(bonferroni,fisher's LSD) after oneway and anova. But what
> if I conduct nonparmetric kruskall wallis test and then do multiple
> comparison, what should I do?
The adjustments of the p-value like Bonferroni, Holm, and Sidank's
adjustment are general and can also be used after non-parametric tests.
The adjustments are (n = number of tests, p = p-value, p' = adjusted
p-value):
bonferroni (Bonferroni's method)
p' = min(1, np)
holm (Holm's method)
p' = min(1,n(p)*p),
where n(p) is the number of p-values smaller than p
sidak (Sidak's method)
p' = 1 - (1-p)^n
See: -help _mtest-
-- Maarten
-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands
visiting address:
Buitenveldertselaan 3 (Metropolitan), room N515
+31 20 5986715
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
