Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

re: st: Repeated measures ANOVA with mutually dependent variables


From   David Airey <david.airey@Vanderbilt.Edu>
To   statalist@hsphsun2.harvard.edu
Subject   re: st: Repeated measures ANOVA with mutually dependent variables
Date   Mon, 27 Aug 2007 09:59:26 -0500

.

I have the following subtracted electrophysiological data from three conditions
a-b, a-c, and b-c, and I would like to know if it is feasible to introduce in
the same repeated measures ANOVA these subtracted variables since they are
mutually dependent? or if doing so I am violating the ANOVAís assumptions.
Please, provide me also with some references where I can read about this issue.

I would extremely appreciate your valuable help,

Selene Cansino
Using completely determined regressors in regression can cause it to fail. Suppose you make three 0,1 indicator variables for three groups, and then use all of them instead of two of them in a regression. It will fail if you use all three. You should use two and leave one out for the comparison group. Run your model and see! As for assumptions, use diagnostic plots and tests to establish if the assumptions have been met, once you establish the model doesn't fail because of a singularity.

-Dave
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/




© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index