Skip to main content
Fig. 3 | BMC Biology

Fig. 3

From: Machine-learning strategies for testing patterns of morphological variation in small samples: sexual dimorphism in gray wolf (Canis lupus) crania

Fig. 3

Dorso-ventral view shape models reconstructed at the extreme ends of the distribution of EFA outline data projected onto the single canonical variate eigenvector (CV-1, see Fig. 2). Note that even at these extremes, the shape distinctions between characteristic male and female morphologies are quite small for this dataset and focus primarily on the lateral extent of the zygomatic arches. It is exceedingly doubtful that sex-based discriminations of this nature could be made reliably by eye. Moreover, since these outlines were interpolated from a subset of the Fourier harmonic data available for these outlines, there is also a question as to whether this putative difference is artifactual, arising as a result of the interaction between the small sample size and the interpolations inherent in shape reconstruction from Fourier harmonic data

Back to article page