[R] nlme: problem with fitting logistic function

[Dieter Menne]

Douglas Bates <bates <at> stat.wisc.edu> writes:

> > 3) Use lmer in lme4. Your mileage may vary, I could not find a speedup
> >   for my problems, but larger problem might give one.
> 
> Did you mean nlmer in the lme4 package?  If so, it may be worthwhile
> trying the development branch but that is not something for the
> faint-hearted.

Thanks, Doug, for you comments. To be fair, I wrote these unordered 
thoughts to get you out of the snowhole :-)
 
> > 4) Use C for the core function. This is very effective, and there is at least
> >   on example coming with nlme (was it SSlogist?).
> 
> Do you think that evaluation of the model function takes a substantial
> portion of the computing time?  I am asking for my interest, not
> because I think I know the answer.  So, for example, have you profiled
> difficult nlme fits and found that the model function evaluation was
> expensive?

No, I did not profile that function, but 8 years ago tried it once because
at that time I thought it would help. Nowadays, I am more inclined to think
that failure of nlme with a more complex model is a failure of the model,
not of nlme; I don't have speed problems with my data.

However, I remember that in a similar case with ode/lsoda, using c function
made a factor of 20++, so I would have a look into it again if speed 
was a concern for me.

Dieter