A primer on simple measures of association taught at undergraduate level

This article discusses and contrasts the measures of association introduced by Pearson, Spearman, and Kendall, as these are the three most commonly used in practice and also the ones primarily covered in introductory statistics courses. Emphasis is placed on concepts pertaining to the measurement of...

Full description

Saved in:
Bibliographic Details
Published in:Teaching statistics 2022-09, Vol.44 (3), p.96-103
Main Authors: Allison, James S., Santana, Leonard, Visagie, I. J. H.
Format: Article
Language:English
Subjects:
Correlation
Correlation coefficients
Higher education
Introductory Courses
Kendall's tau
Measurement
Pearson's correlation
Spearman' rho
Statistics
Statistics Education
Teaching
teaching statistics
Undergraduate Students
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This article discusses and contrasts the measures of association introduced by Pearson, Spearman, and Kendall, as these are the three most commonly used in practice and also the ones primarily covered in introductory statistics courses. Emphasis is placed on concepts pertaining to the measurement of the level of association between two variables, the calculation of the coefficients, and the interpretation of the calculated values. In particular, we demonstrate how Spearman's rho and Kendall's tau can be expressed in terms of Pearson's correlation coefficient based on transformed data. Important concepts and potential pitfalls are illustrated using numerical examples.
ISSN:0141-982X
1467-9639
DOI:10.1111/test.12307