Eleven Ways to Look at the Chi-Squared Coe cient for Contingency Tables

This article has been written in recognition of the 100th aniversary of introduction of the concept of association between categorical variables by Yule and Pearson. The most popular among the contingency coe cients, Pearson's chi-squared, estimates the bias of a cross-classi cation from the statistical independence. Also, it measures association per se between the row and column variables. The purpose of this article is to present a collection of eleven de nitions for the chisquared coe cient related to either of these goals. One of the quoted de nitions of the chi-squared coe cient seems especially appealing as an association measure: the averaged relative Quetelet index of category-to-category associations.