"dennis roberts" <[EMAIL PROTECTED]> wrote in message
[EMAIL PROTECTED]">news:[EMAIL PROTECTED]...
...
> keep in mind that if the data set is symmetrical ... then, trimming really
> accomplishes nothing ... when it comes to the mean ... even if there are
> extreme values ...
This isn't quite correct. The "classic" motivation for using trimmed means
is as estimators of location for heavy-tailed symmetric distributions. It
can be shown that the trimmed mean can be more efficient than the mean in
such cases - sometimes considerably so. (IIRC, there is a good discussion
the efficiency of trimmed means in E. L. Lehmann's _Theory of Point
Estimation_.)
Best regards,
Tim
--
Timothy R. Johnson
Assistant Professor of Statistics
University of Idaho
Moscow, Idaho 83844-1104
[EMAIL PROTECTED]
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
