The lsmeans package can do the comparisons with control for each gene
using something like this:
lsmeans(fitted.model, trt.vs.ctrl ~ trt | gene, ref = 1)
... assuming that the control is the 1st lvel of treatment.
lsmeans does not do the overall F test of treatments at each gene. You
need the multcomp package for that.
I have noticed that pbkrtest can give different df than SAS in cases
where one or more variance components is estimated to be zero -- was
that the case? When tghat happens, SAS pools the corresponding terms
with residual error before getting the df.
Russ
Russell V. Lenth - Professor Emeritus Department of Statistics and Actuarial Science The University of Iowa - Iowa City, IA 52242 USA Voice (319)335-0712 (Dept. office) - FAX (319)335-3017 russell-lenth at uiowa.edu - http://www.stat.uiowa.edu/~rlenth/