[R] Help with NLME

Kent Holsinger kent at darwin.eeb.uconn.edu
Tue Feb 4 17:44:06 CET 2003

I am relatively new to NLME, so the solution to the problem I describe here
may be obvious. But I've spent several days trying to get the right syntax
to formulate random effects for this model appropriately. The full model is:

  nlme(a ~ a.mitscherlich(a.qe, a.max, lcp, light),
       fixed = a.max + a.qe + lcp ~ trt,
       random = a.max + a.qe + lcp ~ 1 | bench/line,
       start = list(fixed=c(17.4305, 0.182444, 0.00928341, -0.00057221,
                            44.8384, 8.67678)),
       method="ML", verbose=T,
       control = nlmeControl(maxIter=250, msMaxIter=200, pnlsMaxIter=20,
                             gradHess=TRUE, returnObject=TRUE, niterEM=100))

What I'd like to do is to compare reduced models with something like

       random = list(a.max ~ 1 | bench, a.qe + lcp ~ 1 | bench/line)

i.e., to drop the nested term on each of the coefficients one by one so that
I can do and anova() to compare the models.

       random = a.max + a.qe +lcp ~ 1 | bench

works fine, but I can't figure out how to drop nested terms from only some
of the coefficients.

Any help (including pointers to appropriate pages in Pinheiro and Bates)
will be much appreciated.



Kent E. Holsinger                kent at darwin.eeb.uconn.edu
-- Department of Ecology & Evolutionary Biology
-- University of Connecticut, U-3043
-- Storrs, CT   06269-3043

More information about the R-help mailing list