|
Abstract: Stable
isotope sourcing is used to estimate proportional contributions of sources to
a mixture, such as in the analysis of animal diets, plant nutrient use,
geochemistry, pollution, and forensics. We will focus our discussion on the
composition of animal diet using the basic linear mixing model. Inference for
this model has been a challenge because there are often many diet sources and
few isotopes, leading to an underdetermined linear system for the diet
probability vector. We consider a Bayesian framework for inference with the
basic mixing model, illustrating the ideas with two examples from the
literature.
This is joint work with Erik Erhardt
of the MIND Institute, Albuquerque
|