Efficiencies and error-rates of Euclidean and Mahalanobis searches in hypergeometries of archaeological ceramic compositions.

摘要

Underlying all archaeological investigations where provenience is inferred from multivariate analytical characterization is the assumption that the group of objects analyzed form a unique set in multivariate hyperspace. In this paper large archaeological ceramic data sets are used to test this assumption. The results clearly demonstrate the dangers of using too few variates, and the power of multivariate matrix-inversion (Mahalanobis) techniques, in the formation of adequately unique groups.