On 15 Jan 2001 17:23:11 GMT, Elliot Cramer <[EMAIL PROTECTED]>
wrote:
> In sci.stat.edu Jim Kroger <[EMAIL PROTECTED]> wrote:
> : Hello, I've received some expert help here on a couple previous occasions
> : (thanks). I have an issue bothering me, which I'd like to present to you.
>
> : I'm doing a two-way, 2X2 ANOVA. Suppose I have 20 subjects, and each has
> : 25 observations of the following types:
>
> no matter how you do it the proper analysis will be equivalent to using
> submect means. adding a replication factor would permit other tests
> (which you are not interested in) but due to their correlation structure
> the tests would not be valid.
As it was stated, Elliot nailed the first question.
A valid ANOVA treats the average (sum) as its starting point.
If this isn't the REAL data, then something else might be true.
If those are 25 0/1 items, then you might do better to model them as
logistic, or something else other than a linear sum - as someone
suggested.
If it is some other data... When you have multiple replications,
sometimes you don't want the *mean* -- for "best single performance"
you might select maximum or minimum. Or you might consider a trimmed
mean. Or best consistency could be indicated by smallest SD, or the
best performance over a specific range (that could be, something about
the Confidence Interval).
--
Rich Ulrich, [EMAIL PROTECTED]
http://www.pitt.edu/~wpilib/index.html
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================