Hostname: page-component-7b7567c8c-9cwtv Total loading time: 0 Render date: 2026-11-19T08:06:26.117Z Has data issue: false hasContentIssue false

Why Pearson's r is Not a Good Similarity Coefficient for Comparing Collections

Published online by Cambridge University Press:  20 January 2017

George L. Cowgill*
Affiliation:
Department of Anthropology, Arizona State University, Tempe, AZ 85287-2402

Abstract

Pearson's coefficient of linear correlation, r, sometimes is used to express the similarity between two archaeological collections when each collection is characterized by the percents of the artifact types it includes. Examples show that r can be extremely misleading when used in this way, and patterns of similarity among a group of collections can be wildly misrepresented. The Brainerd–Robinson statistic is one example of a similarity coefficient that is much better than r for comparing collections.

Résumé

Résumé

El coeficiente de Pearson de correlación lineal, r, se usa a veces para representor la semejanza entre dos colecciones arqueológicas, cuando cada colección esta caracterizada por los porcentajes de los tipos de artefactos incluídos. Ejemplos muestran que r, usado en esta manera, puede ser muy engañoso, y patrones de semejanza dentro de un grupo de colecciones pueden ser muy desfigurados. La estadística Brainerd–Robinson es un ejemplo de un coeficiente de semejanza más apropiado que r para hacer comparaciones entre colecciones.

Information

Type
Reports
Copyright
Copyright © The Society for American Archaeology 1990 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable