Single-Case Design in ABA: A Practical Guide

Single-case design is a way to study one learner over time. It is also called single-subject or N-of-one research. You measure a behavior again and again, before and during a change.

The goal is simple. You want to show that your plan, and not luck, caused the change. Single-case design does this by using the same person as their own comparison. This page explains how it works and why it fits daily ABA practice so well.

Not just for researchers#

Many clinicians think research is separate from their real job. Single-case design shows that line is false. It uses the same thinking you already use with clients. Amber Valentino makes this point directly.

The reasons we use single case design and research are not in any meaningful way different than we would use them in practice. From the talk. Amber Valentino

Think about how you check if a plan works. You take data before you start. You watch the data after you begin. You look for a clear change. That is single-case logic, whether you call it research or not.

Why the graphs convince people#

One big strength of single-case design is how it shows results. It uses graphs, not just numbers in a report. A clean graph makes the change easy to see. Valentino calls this the beautiful part.

This is the beautiful situation, the beautiful thing about a single case design and behavior analysis is that our graphs are incredibly convincing. From the talk. Amber Valentino

A picture of behavior over time is hard to argue with. A parent or funder can see the jump for themselves. The proof is right there on the page. This makes single-case data a strong tool for buy-in.

Cleaner, faster decisions#

Single-case design also speeds up decision-making. When the data are controlled, the answer is clearer. You waste less time guessing. Valentino names this benefit plainly.

When you introduce a single case design, the decision-making is just so much cleaner. It's quicker, it's more efficient. From the talk. Amber Valentino

Compare this to messy, uncontrolled data. With those, you cannot be sure what caused a change. Maybe it was your plan. Maybe it was something else. A single-case design rules out those other causes, so you can act with confidence.

The historical roots#

Single-case design is not a side method in ABA. It is the foundation the whole field was built on. Mark Malady explains where our science came from.

our research foundations were really built on N of one research methodologies and looking at the individual learner in context, rather than using group aggregate data, statistical approaches or methodologies From the talk. Mark Malady

This focus on the individual is not an accident. It reflects a core belief in behavior analysis. Malady ties it to the very idea of the operant.

that individuality is core and critical to the basic concept of the operant From the talk. Mark Malady

So single-case design fits ABA at a deep level. We care about the single person, not the group average. The method matches the science.

How it works in practice#

Single-case designs share a common shape. First you gather baseline data, before any change. This shows the behavior as it stands now. Then you start your plan and keep measuring.

You look for a clear break between baseline and treatment. If the behavior changes only after your plan starts, that is strong evidence. Many designs repeat this pattern to be sure. They add or remove the plan and watch the behavior follow.

Some designs stagger the start across people or settings. This is a multiple baseline design. If each person changes only when their plan begins, the case gets stronger. The repetition is what builds trust in the result.

Common types you will see#

Single-case design is a family of related methods, not one recipe. Each type controls for confounds in its own way. Knowing the main ones helps you read studies and plan your own work.

A reversal design adds and removes the plan over time. If behavior tracks the plan each time, the case is strong. A multiple baseline design staggers the start across people, settings, or behaviors. Change that follows each staggered start rules out chance.

A changing criterion design raises the goal in small steps. Behavior that keeps up with each new step shows control. A multielement design compares conditions quickly, back to back. This is common in functional analysis work.

You do not need every design for every question. You pick the one that fits your setting and your data. The shared goal is always the same. Show that your plan, not something else, moved the behavior.

What the research says#

A common worry is that one person cannot prove much. Researchers push back on this idea. Generality in single-case design comes from repeating a study across people, not from one big group. Behavior analysts can explain this in a short "elevator speech" (Walker, S. G., & Carr, J. E. (2021). Generality of Findings From Single-Case Designs: It’s Not All About the “N”. Behavior Analysis in Practice, 14(4), 991-995. https://doi.org/10.1007/s40617-020-00547-3).

Single-case designs power a wide range of applied studies. One used a multiple baseline design to test a reading intervention for autistic children and children with language delay. Children became more responsive once the intervention began (Bosley, R., Loveall, S. J., Kellum, K. K., & Hawthorne, K. (2024). RECALL prompting hierarchy improves responsiveness for autistic children and children with language delay: a single-case design study. Frontiers in Psychology, 15. https://doi.org/10.3389/fpsyg.2024.1435688).

The method also shows clear cause and effect in staff training. One study used a multiple-probe single-case design to test AI-supported self-coaching for preschool teachers. It found clear functional relations between the coaching and gains in teacher fidelity and child outcomes (Balikci, S. (2026). Investigating the Impact of AI-Supported Self-Coaching as a Professional Development Model for Embedded Instruction in Inclusive Early Childhood Settings. Behavioral Sciences, 16(1). https://doi.org/10.3390/bs16010140).

FAQ#

What is a single-case design? It is a research method that studies one participant over time. The person serves as their own comparison. You measure behavior before and during a change to see if the plan caused the result.

Can you generalize from a single-case design? Yes. Generality comes from replication, not from one large sample. When many studies show the same effect across different people, the finding becomes trustworthy. It is not all about the number of participants.

Why do practitioners use single-case design? It matches the daily work of judging whether a plan works. The graphs make results easy to see and hard to argue with. It also makes clinical decisions faster and cleaner than uncontrolled data.

Mark Malady goes deeper on individualized, learner-centered measurement in genArete: Milestone based comparison criteria in Skill Assessment.