New approaches to the characterization and classification of ceramics on the basis of their elemental composition

The multivariate statistical analysis and XRD analysis of pottery at Xigongqiao site

“…3. Pr, Nd, Gd, Tb, Dy, Ho, Er, Tm, Lu, Y rare earth elements, which have high correlation, so only La, Ce, Sm, Eu, Yb elements are chosen, which accord with the independence of variable [5].…”

Determining the Provenance of native copper artifacts from Northeastern North America: evidence from instrumental neutron activation analysis

“…A tight fingerprint is defined as one where all analyses for each element fall into narrow concentration ranges. To establish how ''tight'' a fingerprint is, the technique provides conditional and expected probabilities (see Vitali and Franklin [112] for an important application of this technique to ceramics). Both SAS and SPSS statistical packages were employed in this study.…”

An approach to the use of packaged statistical programs for cluster, classification, and discriminant analysis of trace element data

“…For instance, the trace element data for different obsidian sources shows considerable heteroscedasticity (Leach and Manly, 1982). On the other hand, in certain cases of trace element analysis of archaeological ceramics, such as the study of ceramic groups from northern Iran (Vitali and Franklin, 1986), the groups exhibited nearly equal dispersion matrices. Therefore, a test for the equality of variance for different groups has to be performed (SPSS DISCRIMINANT and SAS DISCRIM procedures include such tests).…”