Going further

Authors
Affiliation

Floriane Remy

CNRS, Univ. Bordeaux, MCC – UMR 5199 PACEA

Frédéric Santos

CNRS, Univ. Bordeaux, MCC – UMR 5199 PACEA

Many other topics have not been covered in this course, but here are some useful pointers.

  1. In particular when studying sexual dimorphism, you might want to build decisional models to know whether it is possible to predict a qualitative variable (e.g., the sex) from the procrustes coordinates. A wide family of supervised classification methods is available to that end, but the most common is the discriminant analysis (Rencher and Christensen 2012), implemented for instance in the R function Morpho::CVA()1. Its help page provides useful examples.
  2. A closely related method, often used to estimate the geographical origin of an individual, is the use of “typicality probabilities” (Wilson 1981; Mizoguchi 2011), implemented in Morpho::typprobClass().
  3. We did not even mention landmarks-free methods in morphometrics, which were covered in other courses of the summer school.
Back to top

References

Mizoguchi, Yuji. 2011. “Typicality Probabilities of Late Pleistocene Human Fossils from East Asia, Southeast Asia, and Australia: Implications for the Jomon Population in Japan.” Anthropological Science 119 (2): 99–111. https://doi.org/10.1537/ase.090330.
Rencher, Alvin C., and William F. Christensen. 2012. “Discriminant Analysis: Description of Group Separation.” In Methods of Multivariate Analysis, 281–308. John Wiley & Sons, Ltd. https://doi.org/10.1002/9781118391686.ch8.
Wilson, S. R. 1981. “On Comparing Fossil Specimens with Population Samples.” Journal of Human Evolution 10 (3): 207–14. https://doi.org/10.1016/S0047-2484(81)80059-0.

Footnotes

  1. In morphometrics, people often refer to discriminant analysis as “canonical variates analysis”. This is not the standard terminology in mathematics, and is also a bit confusing since this is the name of another statistical method.↩︎