[R] likelihood for new data from fitted nlme object

Andrew Bateman awb42 at cam.ac.uk
Tue Apr 12 13:50:52 CEST 2011

Dear list,

I have a fitted nlme object from which I want to produce estimates of
the (marginal) likelihood for new data, given the fitted model.  I am trying to
cross validate a number of nonlinear mixed effects models, and I would
like to find a way to calculate the marginal likelihood for "virgin"
data quickly.

Since nlme must approximated the marginal likelihood many times when
fitting a model, I feel like there should be an easy way to do this
for new data.

Is there an easy way to get this using the nlme model object?  Is
there a straightforward way to manually generate estimates using
components of the fitted model objects (e.g. using equation 4.2 from
Lindstrom and Bates1990 "Nonlinear Mixed Effects Models for Repeated
Measures Data")?

Many thanks (and apologies if I have failed to conform to any of the
list guidelines),

Andrew Bateman
PhD Candidate
Department of Zoology
University of Cambridge

More information about the R-help mailing list