Median-Based Overlap Analysis for Single Case Data

Abstract

This article takes a further look at the percentage of data points exceeding the median (PEM) analysis method for single-case research data, first presented in this journal by Hsen-Hsing Ma. Ma examined the relationship between PEM and the established percentage of nonoverlapping data (PND) and then applied PEM in a meta-analysis of 61 data sets, correlating their authors' judgments of intervention effectiveness with PEM. The present article covers PEM's historical and statistical context and then applies the new measure in a field test with 165 contrasts between a baseline phase A and a treatment phase B. For comparison, Pearson r , Kruskal-Wallis W, PND, and IRD (improvement rate difference) indices also are calculated and correlated with PEM, and all distributions are examined. Expert visual analysis ratings of the 165 graphs are correlated with all indices. PEM surpassed PND in its validation by other established measures. However, PEM was weaker in distribution shape and visual judgment validation. More strongly validated than either PEM or PND was the new nonparametric measure, IRD.