Advancing the Application and Use of Single-Case Research Designs: Reflections on Articles from the Special Issue

Horner and his team read every article in a special issue on single-case designs. They wrote a short reflection paper that lists what the field must do better.

They looked at how we design studies, analyze data, and share results. The paper is a roadmap, not a new experiment.

The authors found three weak spots. First, many studies still use shaky designs that let bias sneak in. Second, analysts rely too much on eye-balling graphs instead of numbers. Third, reports often skip details other scientists need to copy the study.

They say tighter rules for design, stats, and writing will make our work more trusted and easier to replicate.

Jacobs (2019) already told us to swap t-tests for randomization tests in single-case work. Horner et al. (2022) echo that call, so the two papers line up.

Manolov et al. (2022) give a free visual tool that checks if effects repeat across kids. Horner’s paper urges better replication checks, and Manolov delivers the actual tool—an example of practice catching up to advice.

Manolov (2026) goes even further. Four years after Horner’s plea for easier stats, this tutorial hands BCBAs free websites that run the analyses Horner wants. It extends the 2022 standards into click-button reality.

Lanovaz et al. (2017) showed you need at least three A points and five B points to keep false positives low. Horner’s summary nods to such clear decision rules, pulling earlier math into the bigger standards story.

If you run or read single-case studies, this paper is your checklist. Use randomization tests, graph within-session data, and share your data. These steps move our field from "trust me" to "here’s the proof." Your next study can hit all three targets and still be done by Friday.