Rich Ulrich wrote:
<SNIP>
> I think the problem comes down to this: in a small sample (or one
> with an extreme outlier), such a strategy fails because it
> over-capitalizes on chance. (Dealing with an outlier is not a trivial
> matter.) In a large, healthy sample, the ANOVA is robust, or a
> simpler, intentional transformation can be defended. Also, the Ideal
> transformation may fall outside of that family.
I'd echo what Rich wrote. The "ideal" transformation depends on the outcome
that you desire. You could in theory seek a transformation which produces the
desired outcome from _any_ data set. I'm not too happy about any
transformation that doesn't have some meaningful interpretation or defensible
rationale. For example, Log transformations change the model from an additive
to a multiplicative one and are often sensible choices on those grounds alone
(e.g. for time data). Some transformations (e.g. arcsin for proprtions) are
used as a fix for problems with data and may be defended as common practice
(though some recent posts here argued cogently that there is now little excuse
not to use logistic regression in preference).
Thom
===========================================================================
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/
===========================================================================
