Factorial Single-Subject Experimental Design
Also known as: factorial SCED, factorial single-case design, factorial N-of-1 design, factorial within-subject experimental design
A factorial single-subject experimental design applies the logic of factorial experiments — manipulating two or more independent variables simultaneously to study main effects and interactions — within a single-subject (N=1 or small N) repeated-measures framework. Instead of comparing groups, the same individual serves as their own control across systematically varied conditions, enabling fine-grained analysis of how multiple treatment components combine to influence behavior or clinical outcomes.
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 factorial single-subject experimental design when you need to evaluate two or more treatment components or independent variables simultaneously in a population where large samples are unavailable or ethically impractical — common in applied behavior analysis, special education, rehabilitation, and clinical psychology. It is especially appropriate when the research question concerns whether factors interact (e.g., does Component A work better with or without Component B?). Do not use this design when the target behavior is highly reactive to condition changes and cannot return to a stable baseline between phases (ruling out reversal-based structures), or when carry-over effects make it impossible to cleanly isolate the effect of each factorial combination. Group factorial designs are preferable when statistical generalization to a population is required.
Strengths & limitations
- Examines main effects and interactions of multiple independent variables without needing a large sample.
- Eliminates between-subject variability — each participant serves as their own control, increasing internal validity for the individual.
- Well-suited to clinical, special-education, and rehabilitation contexts where participant scarcity makes group designs impractical.
- Continuous repeated measurement provides a rich, time-series picture of how behavior changes as conditions are altered.
- Findings can have immediate clinical relevance because they are derived from actual treatment-relevant individuals rather than group averages.
- Findings describe the individual(s) studied and cannot be statistically generalized to a population without systematic replication across multiple participants.
- Increasing the number of factors rapidly multiplies the number of conditions, demanding more phases and more participant time, which may not be feasible.
- Carry-over and sequence effects are a persistent threat — earlier conditions may alter responding in later conditions in ways that are not fully reversible.
- Visual analysis of time-series data, while standard, is susceptible to analyst bias; supplementing with effect-size statistics is increasingly expected.
- Requires behavioral or clinical targets that can be measured repeatedly and that show sensitivity to condition changes within a realistic timeframe.
Frequently asked
How is this different from a standard single-subject design?
A standard single-subject design (e.g., ABAB or multiple baseline) manipulates one independent variable — treatment present or absent. A factorial single-subject design simultaneously manipulates two or more independent variables across conditions, allowing evaluation of main effects and their interaction within the same individual.
How many participants do I need?
The design is valid with as few as one participant, but replication across three to five individuals is strongly recommended to establish external validity and rule out idiosyncratic effects. Guidelines from What Works Clearinghouse require at least three demonstrations of effect across participants, settings, or time points.
Can I use standard ANOVA to analyze the results?
No — standard ANOVA assumes independent observations, but repeated measurements on the same individual are autocorrelated. Use single-case effect sizes (Tau-U, PND, PAND) for visual-analysis supplements, or multilevel models that account for the nested, time-series structure of the data.
What if behavior does not return to baseline between conditions?
If the target behavior is irreversible or carry-over is severe, a reversal-based factorial structure is not appropriate. Consider embedding the factorial logic within a multiple baseline design, where different factor combinations are introduced at different time points across settings or behaviors, avoiding the need for behavioral reversal.
How many conditions will I have with two factors?
A fully crossed 2x2 factorial design produces four conditions (A1B1, A1B2, A2B1, A2B2), each requiring a stable phase. With two three-level factors you have nine conditions. Fractional replication or sequential component analysis can reduce the condition count when full crossing is impractical.
Sources
- Kazdin, A. E. (2011). Single-Case Research Designs: Methods for Clinical and Applied Settings (2nd ed.). Oxford University Press. ISBN: 978-0195341881
- Barlow, D. H., Nock, M. K., & Hersen, M. (2009). Single Case Experimental Designs: Strategies for Studying Behavior Change (3rd ed.). Pearson. ISBN: 978-0205474554
How to cite this page
ScholarGate. (2026, June 3). Factorial Single-Subject Experimental Design. ScholarGate. https://scholargate.app/en/experimental-design/factorial-single-subject-experimental-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.
- ABAB designExperimental design↔ compare
- Crossover Single-Subject Experimental DesignExperimental design↔ compare
- Factorial ExperimentExperimental design↔ compare
- Factorial Randomized Controlled TrialExperimental design↔ compare
- Multiple Baseline DesignExperimental design↔ compare
- Single-Subject Experimental DesignExperimental design↔ compare