Selecting the proper Tau-U measure for single-case experimental designs: Development and application of a decision flowchart

Abstract

A variety of measures have been developed to quantify intervention effects for single-case experimental design studies. Within the family of non-overlap indices, the Tau-U measure is one of the most popular indices. There are several Tau-U variants, each one calculated differently. The appropriateness of each Tau-U variant depends upon the data characteristics present within the study (e.g. number of measurement occasions, the within-case variability, and baseline trend). However, inconsistent terminology is used to refer to the Tau-U variants, and researchers can overlook the attributes of the different Tau-U variants. As a result, the Tau-U variants can be applied inappropriately, and this can result in invalid conclusions of intervention effectiveness. This paper proposes a Tau-U flowchart that can assist the decision-making process when using Tau-U with single-case experimental designs that incorporate baseline-intervention (AB) comparisons (e.g. multiple-baseline designs, withdrawal/reversal designs, etc.). The flowchart can help researchers select the appropriate Tau-U variant to use based on their data and research questions. The flowchart is applied to two single-case experimental studies to demonstrate its use.

Keywords:

• Decision-making tool
• Effect size
• Meta-analysis
• Single-case experimental designs
• Tau-U
• Tau-U decision flowchart

Disclosure Statement

No potential conflict of interest was reported by the author(s).

Notes

¹ This review was limited to the database PsycINFO.

² See Fingerhut et al. (2021) for details about the Critical Tau-U method.

³ It is possible that different Tau-U variants would be most appropriate for use for different AB phase contrasts. For example, if one AB block has trend in the A (baseline) phase, but the other AB block does not have trend in the A phase, the researcher would need to use two different Tau-U variants for the estimates of each separate AB phase contrast.

Additional information

Funding

This research was supported by the Institute of Education Sciences, U.S. Department of Education, through grant R305D190022. The content is solely the responsibility of the author and does not necessarily represent the official views of the Institute of Education Sciences, or the U.S. Department of Education.