Bayesian stable isotope mixing models

TLDR

Stable isotope mixing models quantify the proportional contributions of various sources to a mixture, most commonly used to estimate organism diets from observed food sources. This paper reviews recent advances in SIMMs and embeds them within a Bayesian statistical framework to enable useful extensions. The authors construct a multivariate Bayesian model centered on a compositional mixture of food sources corrected for metabolic factors, employing an isometric log‑ratio transform that permits time‑series and non‑parametric smoothing, and demonstrate the approach with three real animal dietary case studies. © 2013 John Wiley & Sons, Ltd.

Abstract

In this paper, we review recent advances in stable isotope mixing models (SIMMs) and place them into an overarching Bayesian statistical framework, which allows for several useful extensions. SIMMs are used to quantify the proportional contributions of various sources to a mixture. The most widely used application is quantifying the diet of organisms based on the food sources they have been observed to consume. At the centre of the multivariate statistical model we propose is a compositional mixture of the food sources corrected for various metabolic factors. The compositional component of our model is based on the isometric log‐ratio transform. Through this transform, we can apply a range of time series and non‐parametric smoothing relationships. We illustrate our models with three case studies based on real animal dietary behaviour. Copyright © 2013 John Wiley & Sons, Ltd.