Cliff‘s Delta: A Non-parametric Effect Size Measure

In psychological and social science research, comparing two sets of data to understand their differences is a common task. Cliff's Delta (or simply Delta) is a valuable tool used to quantify the magnitude of these differences, without relying on assumptions about data distribution.

Introduction

Cliff's Delta is an effect size measure used to compare the differences between two groups of data. Unlike traditional t-tests or analysis of variance (ANOVA), it is non-parametric and does not assume specific distributions of data. This makes it particularly useful when dealing with small sample sizes or non-normally distributed data.

Basic Principles

Cliff's Delta operates on the following principles to compute the effect size between two groups of data:

1. Data Sorting: Sort both sets o