[R-sig-ME] RLRsim example

fengsj at mail.utexas.edu fengsj at mail.utexas.edu
Tue Jun 1 19:13:12 CEST 2010

Hi all,
I want to compare different glmer fits.  I read examples about  
comparing models by anova() for lmer fits and this method may not be  
accurate.  I have been checking the Package ‘RLRsim’ to do the test. I  
am very confused  by  the example from the package reference:

mA <- lmer(Reaction ~ I(Days-4.5) + (1|Subject) + (0 +  
I(Days-4.5)|Subject), sleepstudy)
m0 <- update(mA, . ~ . - (0 + I(Days-4.5)|Subject))
m.slope <- update(mA, . ~ . - (1|Subject))
#test for subject specific slopes:
## Not run: exactRLRT(m.slope, mA, m0)

First of all, what does it mean “not run” there? (when I did run  
exactRLRT(m.slope, mA, m0), I got error messages) . Then , what should  
be run?

Suppose I want to test if there is siginficant random slope based on I  
already have the random intercept, what should I do with exactRLRT?

Thanks so much!

More information about the R-sig-mixed-models mailing list