Problems in Logic and Interpretation with Quantitative Syntheses of Single-Case Research: Mathur and Colleagues (1998) as a Case in Point

This article focuses attention on some of the logic and interpretation problems inherent in doing quantitative syntheses of single-case research. Particular attention is given to the meta-analytic method of using percentage of nonoverlapping data, highlighting specific concerns related to withdrawal designs, sensitivity to variability in behavior, social significance of behavior change, and understanding the complex multiple variables that influence intervention effectiveness. As a case in point, we critique the use of PND in an article by Mathur, Kavale, Quinn, Forness, and Rutherford (1998) recently published in Behavioral Disorders.