Single-blind Single-Subject Experimental Design
Also known as: single-blind N-of-1 design, SB-SSED, single-blind within-subject design, single-blind single-case experimental design
A single-blind single-subject experimental design (SB-SSED) applies a single-blind protocol to an N-of-1 experiment: one individual participant is studied intensively across alternating or sequential phases, and either the participant or the assessor — but not both — is kept unaware of the current treatment condition. This design combines the idiographic power of single-subject methodology with a structured blinding control to reduce performance or assessment bias, and is common in applied behavior analysis, clinical psychology, and rehabilitation research.
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 single-blind single-subject experimental design when the research or clinical question concerns the effect of an intervention on a single individual (or a very small set of individuals studied independently), repeated measurement is feasible, and expectancy bias from either the participant or the assessor is a plausible confound. It is well suited to behavioral interventions in clinical, educational, and rehabilitation contexts. Do not use this design when group-level generalization is the primary aim, when repeated measurement would cause fatigue or reactivity that cannot be controlled, when neither participant nor assessor blinding is practically possible, or when a carryover (order) effect from alternating conditions cannot be ruled out — in that last case an ABA or ABAB design with washout periods, rather than an alternating treatments design, should be considered.
Strengths & limitations
- Combines within-person causal inference with a blinding control that reduces expectancy and observer bias.
- Requires only one participant, making it feasible when the target population is rare or when individualised treatment evaluation is the goal.
- High-frequency repeated measurement detects change trajectories that pre-post designs miss.
- Replication across phases within the same participant provides internal evidence of causality without a separate control group.
- Applicable in clinical practice as a formal N-of-1 trial framework to guide individual treatment decisions.
- Findings are specific to the individual; external generalizability requires systematic replication across multiple participants.
- Single blinding leaves one party unblinded, preserving residual bias risk compared with a double-blind design.
- Carryover effects — when a previous phase influences the next — can invalidate phase comparisons, particularly in alternating treatment designs.
- Maintaining a credible blind over extended phase sequences in naturalistic settings is practically difficult.
- Visual inspection, the primary analytic tool, is subjective; inter-rater disagreement on trend significance is common.
Frequently asked
How is single blinding achieved in a single-subject design?
The most common approach is to blind the assessor: a separate rater who scores videos or behavioral records without knowledge of the current phase. Participant blinding is feasible when the treatment can be disguised (e.g., active versus placebo capsules in a pharmacological N-of-1 trial) but is impractical for most behavioral interventions where the participant is necessarily aware of what they are doing.
What is the minimum number of data points needed per phase?
The general recommendation is a minimum of three to five data points per phase to assess stability before transitioning, though more is preferred. Some methodologists recommend continuing a phase until the trend is clearly stable and unambiguous, rather than applying a fixed number. In alternating treatment designs each condition is presented multiple times and the total data points per condition should be sufficient to distinguish condition means from within-phase variability.
Is single-subject design the same as a case study?
No. A case study is a descriptive, naturalistic account that does not require prospective experimental manipulation or repeated standardized measurement. A single-subject experimental design requires pre-specified phase sequences, stable baseline establishment, controlled introduction of the intervention, and systematic repeated measurement — criteria that give it internal validity that descriptive case studies lack.
When should I choose a double-blind design instead?
Choose a double-blind design when both participant expectancy and assessor bias are plausible threats and when the intervention can be concealed from both parties — for example, pharmacological N-of-1 trials with identical-looking active and placebo preparations. Single blinding is a reasonable compromise when full blinding is not feasible, but the residual bias from the unblinded party should be acknowledged as a limitation.
Can I use inferential statistics with this design?
Yes. While visual inspection remains the primary and most defensible analytic tool in single-subject research, effect-size statistics such as Tau-U, non-overlap of all pairs (NAP), or percentage of non-overlapping data (PND) are widely used. Interrupted time-series regression can model level and trend changes at phase transitions. These supplement — rather than replace — visual analysis and are particularly useful when reporting findings to audiences unfamiliar with single-subject conventions.
Sources
- Barlow, D. H., & Hersen, M. (1984). Single case experimental designs: Strategies for studying behavior change (2nd ed.). Pergamon Press. ISBN: 978-0080302378
- Kazdin, A. E. (2011). Single-case research designs: Methods for clinical and applied settings (2nd ed.). Oxford University Press. ISBN: 978-0195341881
How to cite this page
ScholarGate. (2026, June 3). Single-blind Single-Subject Experimental Design. ScholarGate. https://scholargate.app/en/experimental-design/single-blind-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.
- AB DesignExperimental design↔ compare
- ABA DesignExperimental design↔ compare
- ABAB designExperimental design↔ compare
- Multiple Baseline DesignExperimental design↔ compare
- Single-blind Randomized Controlled TrialExperimental design↔ compare
- Single-Subject Experimental DesignExperimental design↔ compare