[R-sig-ME] Using residuals to test for random effect

Max Reuter m.reuter at ucl.ac.uk
Wed Apr 6 09:09:00 CEST 2011

Hi Fabian,

Many thanks for your reply. I have installed lme4a yesterday and will have a look at the profiling.

All the best, Max

> Hi,
> The fact that the results depend on the type of residuals you use sugest to
> me that the procedure is not trustworthy - I'm not aware of any paper
> investiating the properties of this approach. This also suggests that a
> statistical reviewer worth his/her salt would call you out on using
> something so completely ad-hoc.
> I'd go with a parametric bootstrap test of the variance component or the
> profiling approach that is implemented in lme4a.
> Fabian Scheipl
> (author of RLRsim)

Max Reuter
Research Department of Genetics, Evolution and Environment
Faculty of Life Sciences
University College London
4 Stephenson Way
London NW1 2HE, UK

Phone: +44-20-76795095 (internal 25095)

Lab: http://www.homepages.ucl.ac.uk/~ucbtmre/Labsite/
Department: http://www.ucl.ac.uk/gee

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