Effect size measures for single-case research: Conceptual, practical, and statistical considerations

Quantitative analysis of single-case research and n-of-1 experiments often focuses on calculation of effect size measures, or numerical indices describing the direction and strength of an intervention’s effect on an outcome for the participating cases. Many different effect size measures have been proposed specifically for use with single-case research designs—so many, in fact, that researchers may find it difficult to choose among the wide array of options that have been proposed. In this talk, I will first discuss the purpose of using effect size measures and highlight some conceptual considerations that should inform the choice among available measures. I argue that effect size measures should be selected by considering the properties of the outcome variable, the anticipated form of intervention’s effect on that outcome, and the level of analysis (i.e., individual-level or study-level) in order to identify an index that is interpretable and can be meaningfully compared from one study to another. I then survey some of the available effect size measures, highlight practical tools for carrying out the calculations, and discuss some of the statistical issues that arise in applying effect sizes to data from single-case and n-of-1 designs.