Pilot ABAB Design — Pilot Reversal Single-Subject Experimental Design
Pilot ABAB Reversal Design · Also known as: pilot reversal design, feasibility ABAB design, pilot withdrawal design, pilot single-subject reversal
A Pilot ABAB design is a small-scale feasibility trial of the ABAB reversal design, conducted with one or a few participants to test whether an intervention produces reliable behavior change under alternating baseline and treatment conditions before committing resources to a larger study. It combines the internal-validity logic of the ABAB reversal with the limited scope and preliminary aims of a pilot investigation.
Read the full method
Sign in with a free account to read this section.
Method map
The neighbourhood of related methods — select a node to explore.
When to use it
Use a Pilot ABAB design when you need to evaluate the feasibility of implementing a reversal single-subject design before a full study, especially in applied behavior analysis, behavioral intervention research, or clinical behavioral sciences. It is appropriate when the target behavior is expected to be reversible upon withdrawal of the intervention, the researcher needs preliminary effect-size estimates, and resources preclude a full-scale ABAB study. Do not use it when the behavior change is intended to be permanent and irreversible (extinction of a skill does not make withdrawal ethical or informative), when carryover effects are expected across phases, when the research question requires causal conclusions rather than feasibility data, or when multiple-baseline designs are more appropriate (e.g., for irreversible learning outcomes).
Strengths & limitations
- Provides rigorous within-subject causal evidence even with a single participant, avoiding the need for a matched control group at the pilot stage.
- Generates concrete feasibility data — fidelity, burden, measurement reliability — that directly improve the design of a subsequent full study.
- Produces preliminary effect-size estimates (PND, Tau-U) usable for power analysis planning.
- Efficient use of resources: a small, short pilot can prevent costly design failures in a larger trial.
- Replication of effect across two B phases substantially strengthens causal inference within the pilot itself.
- Requires that the target behavior be reversible when the intervention is withdrawn; many learning outcomes or skill acquisitions are not ethically or practically reversible.
- Small participant numbers limit external generalizability; findings cannot be extrapolated to a population without a subsequent larger study.
- Phase length decisions in a pilot are inherently arbitrary, which can affect whether stable patterns emerge.
- Carryover or sequential confounds can blur the A2 reversal if the behavior is influenced by history effects.
Frequently asked
How many participants do I need in a Pilot ABAB design?
Typically one to three participants for a true pilot. The goal is not statistical power but feasibility assessment and preliminary effect data. If you find promising and consistent effects across even two or three participants, that supports moving to a larger study.
How long should each phase be?
A minimum of five data points per phase is the conventional guideline in single-subject research to detect a stable trend. In a pilot, phases may be shortened relative to a definitive study, but each phase should still reach a stable level or clear trend before moving forward. Rushing phases is a common error that undermines the reversal logic.
What effect-size statistics can I report from a Pilot ABAB?
The most common non-overlap indices are Percentage of Non-Overlapping Data (PND), Percentage of All Non-Overlapping Data (PAND), and Tau-U, which adjusts for baseline trend. These provide standardized effect-size estimates suitable for use in power analysis for a subsequent full trial.
Is a Pilot ABAB ethical when withdrawal means removing a beneficial treatment?
This is a core ethical concern. The design is only appropriate when withdrawal is temporary and does not cause lasting harm. If the intervention targets an irreversible skill, a medically critical behavior, or a situation where withdrawal poses risk, a multiple baseline design is the ethical alternative.
How is a Pilot ABAB different from a standard ABAB design?
The logic and phase sequence are identical. The difference is in purpose and scope: a standard ABAB is a definitive investigation of causal effect, whereas a Pilot ABAB explicitly aims to assess feasibility, refine procedures, and generate preliminary data. Pilot studies have smaller samples, may have shorter phases, and report feasibility metrics alongside behavioral outcomes.
Sources
- Byiers, B. J., Reichle, J., & Symons, F. J. (2012). Single-subject experimental design for evidence-based practice. American Journal of Speech-Language Pathology, 21(4), 397–414. DOI: 10.1044/1058-0360(2012/11-0036) ↗
- Barlow, D. H., Nock, M. K., & Hersen, M. (2009). Single Case Experimental Designs: Strategies for Studying Behavior Change (3rd ed.). Allyn & Bacon. ISBN: 978-0205474554
How to cite this page
ScholarGate. (2026, June 3). Pilot ABAB Reversal Design. ScholarGate. https://scholargate.app/en/experimental-design/pilot-abab-design
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
- AB DesignExperimental design↔ compare
- ABA DesignExperimental design↔ compare
- ABAB designExperimental design↔ compare
- Multiple Baseline DesignExperimental design↔ compare
- Pilot Randomized Controlled TrialExperimental design↔ compare
- Single-Subject Experimental DesignExperimental design↔ compare