On Wed, 26 Jan 2000, Rob Smith inquired ...
> ... concerning power analysis [for] a Kruskal-Wallis test.
Observing that
> When I run an ANOVA on these same data, the p-value is nearly the
> same as for the Kruskal-Wallis,
he wondered
> ... if it would be reasonable to use the power analysis from the
> parametric test as an estimate of the power of the nonparametric test.
> This idea is attractive to me because I can find information on the
> power of ANOVA in my textbooks. What would you do? Thanks in advance.
A rough estimate is better than no estimate at all.
OTOH, why are you avoiding ANOVA in favour of K-W? Do you really have
compelling reason(s) for K-W? (E.g., are the cell residuals visibly and
emphatically non-normal?) ANOVA is more flexible in allowing one to
accommodate to other categories in the data (even if one has sometimes
to run a regression analysis with indicator variables as predictors when
the underlying ANOVA design is unbalanced), and to pursuing a variety of
imaginable post hoc questions.
-- DFB.
------------------------------------------------------------------------
Donald F. Burrill [EMAIL PROTECTED]
348 Hyde Hall, Plymouth State College, [EMAIL PROTECTED]
MSC #29, Plymouth, NH 03264 603-535-2597
184 Nashua Road, Bedford, NH 03110 603-471-7128
===========================================================================
This list is open to everyone. Occasionally, people lacking respect
for other members of the list send messages that are inappropriate
or unrelated to the list's discussion topics. Please just delete the
offensive email.
For information concerning the list, please see the following web page:
http://jse.stat.ncsu.edu/
===========================================================================
