Have you checked Pinhiero and Bates (2000) Mixed-Effects Models in S
and S-Plus (Springer)? This is the primary documentation for "lme" and
includes, I believe, the answer to this question and many others. Doug
Bates is the primary developer of "lme" in conjunction with several of
his graduate students including Jose Pinhiero.
Doug is also arguably the leading figure in nonlinear regression,
having explained carefully the difference between intrinsic and
parameter effects nonlinearity. Bates and Watts (1988) Nonlinear
Regression Analysis and Its Applications (Wiley) include a table in a
later chapter showing that for 30-60 published data sets they analyzed,
the parameter effects were roughly 10 times the intrinsic curvature.
This means that profiling produces much more accurate confidence regions
than using any neg inverse Hessian, and within the latter, a smart
selection of transformation like log(variances) will produce much more
accurate confidence regions than without.
Sorry I couldn't just give you the fish you wanted, but the fishing
equipment I mentioned may help you more in the long run.
Best Wishes,
spencer graves
Sven.Knudsen@adeptscience.dk wrote:
Dear S group
I am currently evaluating the S-PLUS lme fucntion. The output I try to
recreate is from PROC MIXED (SAS version 6.1). As far as I can
understand, the two procedures base standard errors of variance
components on minus the invers of the Hessian matrix; at lesat that is
what the intervals method for lme object does. However, the std. erros
differ from the SAS out put when extracted from an lme object via
sqrt(diag(lme.obj$apVar)). Am I doing something wrong here?
Few years ago, I heard a roumer that SAS did compute these values with
error - is this what I am discovering here with SAS version 6.1?
Adept Scientific ApS
Sven Jesper Knudsen
Senior Consultant
|