On 27 Jan 2004 14:08:21 GMT, [EMAIL PROTECTED] (Jkd304) wrote:

> I'm fitting a repeated measures mixed model, so the explanatory variables are
> the same for each variate. The subjects can be categorized into group A, B, C
> etc.

That seems to  indicate:  
multiple (randomized treatment? cross-sectional survey?)  groups
by multiple time periods/ conditions
by multiple variables.

That is more complicated than a beginner should begin with, 
so, I hope that you can use my terms to describe your data
in terms that won't confuse me so much....

> Each group has a number of fixed effects parameters. I'm testing whether the
> mean values of the estimated parameters in each group are different over all
> responses, but i don't know the best way to describe the test. For instance, am
> i testing whether the within subject and within group estimated mean values are
> significantly different.


-- 
Rich Ulrich, [EMAIL PROTECTED]
http://www.pitt.edu/~wpilib/index.html
"Taxes are the price we pay for civilization." 
.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
.                  http://jse.stat.ncsu.edu/                    .
=================================================================

Reply via email to