[R] baseline category logits

[Grathwohl,Dominik,LAUSANNE,NRC/NT]

Dear all,

I have a question about baseline category logits.
My data is about colors of infant stools. 
Stools can be brow, green or yellow.
Color of stools is collected at 4 visits. 
However, at visits only marginal information 
is available, not the sequence of color.
E.g. sequence: YYYYYBYBY is collapsed to 2B, 0G, 7Y.
Infants are randomized to two infant formula groups
(for1, for2) in a factorial design. Question of 
interest is, whether one of the two formula can 
influence the color of stools.

The data looks like:

     for1 for2 visit1    visit2    visit3    visit4
----------------------------------------------------
subj |   |   | B  G  Y | B  G  Y | B  G  Y | B  G  Y  
------------------------------------------------
   1 | 0 | 0 | 2  0  7 | 0  0  5 | 0  0  3 | 0  0  4
   2 | 0 | 0 | 0  0 13 | 0  2 15 | 0  0 13 | 0  0 10
   3 | 0 | 1 | 1  1 17 | 0  0 17 | 1  0 10 | 0  0  9
   4 | 0 | 1 | 0  0 10 | 0  0 10 | 0  5 11 | 0  6  9
...
  31 | 1 | 0 | 2  0  7 | 0  0  1 | 0  0  0 | 0  0  0
  32 | 1 | 0 | 0  0  3 | 0  0  5 | 0  0  3 | 0  0  5
  33 | 1 | 1 | 0  0 10 | 0  0 11 | 0  0  3 | 0  0  3
  34 | 1 | 1 | 0  0  9 | 0  0  9 | 0  0  8 | 0  0  3
...

I am thinking of a baseline category logits model 
like Agrestis Alligator Food Choice Example in the
(1996) book, but additional with some time dependency.
Perhaps, random effects could be useful 
to model time dependency.

Alternatively, I can handle every color as a separate 
variable, doing three separate longitudinal analysis, 
one of yellow stool counts, one for green stool counts 
and one for brown stool counts.

Every help would be appreciate, 
perhaps someone could point me to a similar example.

Kind regards, 

Dominik 


Dominik Grathwohl 
Biostatistician 
Nestlé Research Center 
PO Box 44, CH-1000 Lausanne 26 
Phone: + 41 21 785 8034 
Fax: + 41 21 785 8556 
e-mail: dominik.grathwohl at rdls.nestle.com 


-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._