A general hypothesis‐testing framework for stable isotope ratios in ecological studies

• DOI: 10.1890/09-1454.1
• Publication Date: 2010-06-22T05:04:14Z
• Authors: Thomas F. Turner; Michael L. Collyer; Trevor J. Krabben...
• Keywords: Univariate; Biplot; Centroid; Sample (material)

We propose a framework for hypothesis-testing of stable isotope ratios in ecological studies. Statistical procedures are based on analysis nested linear models and residual permutation procedure (RPP) that is employed to evaluate probabilities associated with test statistics. used simulated examples real data set illustrate the utility generality method. First, we developed differences centroid location dispersion delta13C delta15N values within among groups isotopic data. Second, evaluated magnitude direction change position (termed "path") pair samples separated space/time relative paths other paired sample sets. Third, compared attributes path trajectories (size, direction, shape) over sets containing more than two provide quantitative description how patterns response spatial temporal gradients. Examples limited bivariate case (delta13C-delta15N biplots), but statistical method can readily be applied univariate multivariate cases.