Spearman’s correlation coefficient: The case of duplicate ranks

Abstract

Correlation analysis makes it possible to calculate the dependence of one variable on another. It can be used to calculate the tightness of the relationship between variables. Spearman’s rank correlation coefficient allows you to perform a ranking operation based on features that can be represented numerically, for example expert estimates, consumer preferences. In expert assessments, it is possible to rank the assessments of various experts and find a correlation between these expert assessments. Spearman's correlation coefficient can be used to evaluate the dynamics of expert assessments. The article proposes a formula for calculating Spearman’s rank correlation coefficient with repeated ranks. Spearman’s correlation coefficient is ranked. When calculating them, the relative position of the parameters. However, these parameters do not necessarily have to have a normal distribution.