[R-sig-ME] lmer: ML and REML estimation

dave fournier otter at otter-rsch.com
Sun Mar 29 00:03:17 CET 2009

The original question was:

 "I wondered whether non-linear likelihoods, like those of
the binomial models that I have used, can be estimated with REML
methods or not." which I take to mean "Is there anything analogous to
REML methods for linear mixed models which can be used in  nonlinear
mixed models or for glmm's at the very least)?"

The response the OP got was more or less, no there are not, which I
think is incorrect. The correct answer is yes there are, but with the
caveat that perhaps nobody has investigated whether they have good
properties. (I wonder why not?)

David A. Fournier
P.O. Box 2040,
Sidney, B.C. V8l 3S3
Phone/FAX 250-655-3364

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