Blocked Multiple Baseline Design — Blocked Multiple Baseline Single-Subject Experimental Design
Blocked Multiple Baseline Single-Subject Experimental Design · Also known as: blocked MBD, blocked multiple-baseline, blocked multiple baseline across subjects, blocked SSED multiple baseline
A blocked multiple baseline design is a single-subject experimental approach that combines the logic of the multiple baseline design with blocking — the systematic grouping of participants, behaviors, or settings into matched sets — to reduce extraneous variability and strengthen causal inference. The intervention is introduced in a staggered sequence across baselines within each block, demonstrating experimental control through replication within and across blocks.
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 blocked multiple baseline design when (a) an experimental reversal (withdrawal) of treatment is ethically or practically impossible, (b) you have at least three functionally independent baselines across which intervention effects can be staggered, and (c) participants or conditions differ enough on a nuisance variable that matching into blocks would reduce unwanted variability. It is particularly well-suited to applied behavior analysis, special education, rehabilitation, and clinical psychology where individualized treatment evaluation is the goal. Do not use this design when baselines are not functionally independent — interdependence between targets means intervention effects will spread immediately to untreated baselines, destroying the staggered logic. Also avoid it when only one or two baselines are available; the minimum viable replication requires at least three.
Strengths & limitations
- Demonstrates experimental control without requiring withdrawal of an effective treatment, making it ethically defensible in clinical and educational settings.
- Blocking on a matched variable reduces extraneous variability and increases sensitivity to the intervention effect.
- Replication of the effect across multiple baselines and multiple blocks provides strong evidence of a causal relationship.
- Flexible: can be applied across behaviors, participants, or settings depending on the research question.
- Direct clinical relevance — conclusions apply to individual participants rather than group averages.
- Requires at least three functionally independent baselines, which can be logistically demanding to establish and monitor simultaneously.
- The staggered sequence means some participants or behaviors must wait for intervention while data accumulates in baseline, which raises ethical concerns when treatment is urgently needed.
- Internal validity is threatened if baselines are not truly independent — improvement in one baseline that spreads to others undermines the design logic.
- Statistical analysis of single-subject data remains methodologically contested; visual analysis of graphs is the primary but subjective tool.
Frequently asked
What is blocking and why does it matter here?
Blocking means grouping baselines (or participants) into matched sets before the staggered intervention begins. By pairing participants who are similar on a key nuisance variable — such as baseline performance level — any differences between blocks are held roughly constant within each comparison. This reduces unexplained variability and makes the intervention effect easier to detect, much as matched-pairs designs improve power in group experiments.
How is this different from a plain multiple baseline design?
A plain multiple baseline design applies the staggered intervention sequence across all baselines without any explicit grouping. The blocked version adds a pre-study matching step, grouping baselines into blocks based on a shared characteristic. The core logic — staggered introduction of treatment, demonstration of control through replication — is the same; blocking is an additional structural feature that controls for a known source of variability.
How many baselines do I need?
A minimum of three baselines is the conventional threshold for a multiple baseline design to demonstrate experimental control through replication. For a blocked design you need enough baselines to form meaningful blocks — typically at least two baselines per block and at least two blocks, giving a minimum of four baselines. More baselines strengthen the replication argument but also increase logistical demands.
Can I use this design with group data instead of individual data?
The multiple baseline design is fundamentally a single-subject methodology — its logic depends on repeated measurement of the same unit over time and replication of effects within that unit. If you have multiple groups and want to use blocking, a blocked randomized controlled trial or a stepped-wedge design is more appropriate. Mixed approaches exist but must be justified carefully.
How do I analyze the data?
Visual analysis of time-series graphs is the primary method: you examine level, trend, and variability within and between phases across all baselines. Effect size metrics developed for single-subject research — such as Tau-U, IRD (Improvement Rate Difference), or non-overlap of all pairs (NAP) — can supplement visual analysis. Standard parametric statistics are not directly applicable without additional hierarchical modeling assumptions.
Sources
- Cooper, J. O., Heron, T. E., & Heward, W. L. (2020). Applied Behavior Analysis (3rd ed.). Pearson. ISBN: 978-0134752556
- Baer, D. M., Wolf, M. M., & Risley, T. R. (1968). Some current dimensions of applied behavior analysis. Journal of Applied Behavior Analysis, 1(1), 91–97. DOI: 10.1901/jaba.1968.1-91 ↗
How to cite this page
ScholarGate. (2026, June 3). Blocked Multiple Baseline Single-Subject Experimental Design. ScholarGate. https://scholargate.app/en/experimental-design/blocked-multiple-baseline-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
- Multiple Baseline DesignExperimental design↔ compare
- Single-Subject Experimental DesignExperimental design↔ compare