Comparing Groups
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
One of the most common tasks in data analysis is to compare groups or populations of scores, perhaps simply to see if they are different, or to see if one tends to have larger values than the other. The chapter opens with five examples, showing the critical importance of precise specification of the type of difference one is concerned with. Descriptions are given of some of the most important difference measures and the questions they can answer, including the difference between means, the standardised difference between means, the difference between medians, the exceedance probability, the overlapping coefficient, the Kolmogorov-Smirnov statistic, the Wasserstein distance, the Kullback-Leibler divergence, and the Probability Greater Than. Measures for comparing proportions are described. Two further examples are discussed in detail, the first illustrating how the common strategy of analysing ordinal categorical data by assuming an underlying continuous variable can lead to misleading results, and the second elaborating on an earlier example showing how inappropriate choice of comparison can lead to contradictory conclusions.
Fields of Study & Subjects
Probability and Statistical Research
Statistical Methods and Applications
Statistical Distribution Estimation and Applications
Publication details
- Journal / source
- Chapman & Hall/CRC eBooks
- Pages
- 92–127
- Publication date
- 27 March 2026
- Language
- EN
- Document type
- Book chapter