In response to a question about testing multiple samples for
differences in variance instead of differences in mean,
On 23 May 2000 09:49:42 -0700, [EMAIL PROTECTED] (Jerrold Zar)
wrote:
> There are, for example, multiple-comparison tests for tests analogous to
> the Tukey's, Newman-Keuls, and Dunnett's tests for means. These are
> described in Zar, 1999, Biostatistical Analysis, 4th ed., pp. 231-233.
>
Oops? Jerry, being the writer, is yours the *5th* Edition?
In my copy, 4th Ed.,
page 231 is the start of Chap. 12, which is on the two-factor ANOVA.
Page 208-230 is about multiple comparisons, but that is about means.
Page 202-204 is about homogeneity of variances. And you warn about
the poor performance of those tests, so they shouldn't be relied on
for much.
But you don't describe the Levene test. And, if someone is willing to
explicitly describe the tests, they can test variability starting from
that same principle: start with the difference between each score and
the Mean. Or median. Then you can use Absolute value (Levene) or
squared value or log of the square value.
--
Rich Ulrich, [EMAIL PROTECTED]
http://www.pitt.edu/~wpilib/index.html
===========================================================================
This list is open to everyone. Occasionally, less thoughtful
people send inappropriate messages. Please DO NOT COMPLAIN TO
THE POSTMASTER about these messages because the postmaster has no
way of controlling them, and excessive complaints will result in
termination of the list.
For information about this list, including information about the
problem of inappropriate messages and information about how to
unsubscribe, please see the web page at
http://jse.stat.ncsu.edu/
===========================================================================
