Some comments on compositional data analysis in archaeometry, in particular the fallacies in Tangri and Wright's dismissal of logratio analysis

Abstract

This comment exposes the fallacies in the Tangri and Wright (1993) dismissal of the methodology of logratio analysis of compositional data as dangerous surgery. It suggests that compositional data analysts should pay enough attention to the basic nature of compositional data and some elementary principles underlying coherent study in order to avoid meaningless inferences