Premium
Improving Bayesian isotope mixing models: a response to Jackson et al. (2009)
Author(s) -
Semmens Brice X.,
Moore Jonathan W.,
Ward Eric J.
Publication year - 2009
Publication title -
ecology letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 6.852
H-Index - 265
eISSN - 1461-0248
pISSN - 1461-023X
DOI - 10.1111/j.1461-0248.2009.01283.x
Subject(s) - bayesian probability , mixing (physics) , dirichlet distribution , computer science , statistics , software , source code , ecology , mathematics , biology , physics , mathematical analysis , quantum mechanics , programming language , boundary value problem , operating system
We recently described a Bayesian framework for stable isotope mixing models and provided a software tool, MixSIR, for conducting such analyses ( Ecol . Lett ., 2008; 11 :470). Jackson et al . ( Ecol. Lett. , 2009; 12:E1) criticized the performance of our software based on tests using simulated data. However, their simulation data were flawed, rendering claims of erroneous behaviour inaccurate. A re‐evaluation of the MixSIR source code did, however, uncover two minor coding errors, which we have fixed. When data are correctly simulated according to eqns (1)–(4) in Jackson et al. (2009), MixSIR consistently and accurately estimated the proportional contribution of prey to a predator diet, and was surprisingly robust to additional unquantified error. Jackson et al. (2009) also suggested we use a Dirichlet prior on the source proportion parameters, which we agree with. Finally, Jackson et al. (2009) propose adding additional error parameters to our mixing model framework. We caution that such increases in model complexity should be evaluated based on data support.