[R-sig-ME] R2 for lme

[Christina Bogner]

Hello,

as Dr. Bates already mentioned, you can define different R2. I used the 
formula proposed by Edwards et al (2008): An R-2 statistic for fixed 
effects in the linear mixed model, Statistics in Medicine 27(29): 
6137-6157. He compares a mixed-effects model with an empty model 
containing the same random-effects, but only the intercept as a 
fixed-effect. With his approach, you only need to fit the full model, so 
that the random-effects remain the same. To show the overall "goodness" 
of my models, I calculated the correlation coefficient between the 
fitted and the observed values.

HTH

Christina