Dear all,
>>>>>>>>>>>>
We are trying to analyse a series of 3 experiments for input to a
paper and decided to do a meta analysis of all three experiments. The
version of the paper with the meta-analysis is unwieldy and data-heavy and
we thought we could maybe reduce the amount of experiments and data by using
linear mixed effect regressions with R. We have been unable, however, to work
out how to get collinearity info out of these analyses despite trying
a variety of sources.
Can anyone suggest anything? Can we use similar diagnostics to fixed
effects cases, for example?
>>>>>>>>>>>>>>>>
Many thanks for any suggestions,
Peter Watson
--------------------------------------------------------------------------
"Data! Data! Data! I cannot make bricks without data!"
Sherlock Holmes, Granada TV's "The Copper Beeches"
Peter Watson
MRC Cognition and Brain Sciences Unit
15 Chaucer Road
Cambridge
CB2 2EF
Tel: +44 01223 355294 Ext. 801
Fax: +44 01223 359062
Email: [log in to unmask]
|