Skip to content
Prev 2426 / 20628 Next

Fixed effects only model with lme4

*If* you could trust that the log-likelihoods were generated using the
same additive constants in both cases (which I don't think you can), and
*if* you could trust the straight LRT for comparisons of random effects
(see Pinheiro and Bates 2000, Scheipl, etc., for why it is really closer
to a chi-squared mixture between 0 and 1 df) then you could use logLik()
to extract the loglikelihoods of both models and
pchisq(...,df=1,lower.tail=TRUE) to get a p-value (or divide that
p-value by 2 to use a 0/1-df chi-squared mixture).

  Ben Bolker
Jeroen Ooms wrote: