We have data on % time baboons spend performing various categories of
behaviour, and we want to explore functional relationships between these
%'s and various environmental factors.
I'm looking for a list of alternative methods for analysing these data,
given the constraint that all these %'s sum to 100. Is there a more
recent book than Aitchison J (1986) "The statistical analysis of
compositional data" that anyone can recommend? Is there some method other
than the quasi-likelihood extension of the multinomial logistic model that
anyone can recommend?
Many thanks,
Dr. Mike Weale
School of Biological Sciences
Queen Mary & Westfield College
327 Mile End Road
London E1 4NS
(0171) 775-5555 x4783
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|