[R] Odp: Nonlinear Mixed-Effects Models (DNase)

[Petr PIKAL]

Hi

How did you try to fit the model?

 library(nlme)
> DNase$lconc<-log(DNase$conc)
> head(DNase)
Grouped Data: density ~ conc | Run
  Run       conc density      lconc
1   1 0.04882812   0.017 -3.0194489
2   1 0.04882812   0.018 -3.0194489
3   1 0.19531250   0.121 -1.6331544
4   1 0.19531250   0.124 -1.6331544
5   1 0.39062500   0.206 -0.9400073
6   1 0.39062500   0.215 -0.9400073
> DNase<-groupedData(density~lconc|Run, data=DNase)
> fit<-nlsList(density~SSfpl(lconc, A,B, xmid, scal), data=DNase)
> fit1<-nlme(fit)

> fixef(fit)
        A         B      xmid      scal 
0.0321532 2.3585764 1.4207304 1.0132287 
> ranef(fit)
               A           B         xmid         scal
10  0.0052970445 -0.14330145 -0.111382663  0.033117245
11 -0.0156166995  0.05346347  0.095989293  0.097123510
9  -0.0136680461 -0.12703714 -0.102259590  0.004734638
1  -0.0400504359  0.01866298  0.086672974  0.049350211
4  -0.0344644982 -0.02109811  0.022589390 -0.009372415
8   0.0133393611 -0.16099322 -0.111791065 -0.078766236
5  -0.0122056683 -0.12938379 -0.119769285 -0.047167443
7   0.0320448897  0.02841489  0.079210580  0.045662102
6   0.0467424320 -0.01338672 -0.001926885 -0.023503062
2  -0.0009855356  0.12535679 -0.027580167 -0.081603650
3   0.0195671562  0.36930228  0.190247418  0.010425101
>

works.

Regards

Petr
petr.pikal at precheza.cz

r-help-bounces at stat.math.ethz.ch napsal dne 14.05.2007 18:30:58:

> Hi!
> 
> I tried  to  fit four-parameter logistic model (SSfpl) to DNase data 
based on 
> log(conc) (mixed model) but I never get convergence. Can anyone help me? 
 
> 
> Thanks
> 
> Salomé
> 
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide 
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.