Understanding Individual Subject Differences through Large Behavioral Datasets: Analytical and Statistical Considerations
Stacking lots of single-case data lets you see who needs what without giving up the clarity of individual graphs.
01Research in Context
What this study did
Frankot et al. (2024) wrote a how-to guide for behavior analysts.
They say we should pool thousands of single-case graphs into one giant file.
Then we can use new stats tools to see which kids, clients, or animals respond to which tricks.
What they found
The paper itself is a map, not new data.
It shows that big datasets can keep the sharp look of single-case charts while adding the muscle of large-number math.
The payoff: we can spot hidden client types who need different teaching speeds or rewards.
How this fits with other research
Bachman et al. (1988) once warned that group studies were killing progress in obesity care.
Frankot agrees we lost power, but instead of going back to tiny N=1 studies, they say "go big and stay single" by stacking charts.
Cohen et al. (1993) wanted a short personality quiz to pick the right treatment; Frankot scales that idea with machine-learning clusters from huge files.
Fernandez et al. (2023) showed single-case designs work for zoo welfare; Frankot adds that pooling many zoo charts could reveal which species need which enrichments.
Why it matters
You no longer have to choose between pretty single-case graphs and strong stats.
Start saving every graph you make in a shared spreadsheet.
When you hit a few dozen cases, run a free mixed-model script to see if age, IQ, or reinforcer type predicts faster learning.
Adjust programs for the next client before the first session begins.
Want CEUs on This Topic?
The ABA Clubhouse has 60+ free CEUs — live every Wednesday. Ethics, supervision & clinical topics.
Join Free →Open a shared Excel, paste this month’s graphs, and tag each with client age and reinforcer used.
02At a glance
03Original abstract
A core feature of behavior analysis is the single-subject design, in which each subject serves as its own control. This approach is powerful for identifying manipulations that are causal to behavioral changes but often fails to account for individual differences, particularly when coupled with a small sample size. It is more common for other subfields of psychology to use larger-N approaches; however, these designs also often fail to account for the individual by focusing on aggregate-level data only. Moving forward, it is important to study individual differences to identify subgroups of the population that may respond differently to interventions and to improve the generalizability and reproducibility of behavioral science. We propose that large-N datasets should be used in behavior analysis to better understand individual subject variability. First, we describe how individual differences have been historically treated and then outline practical reasons to study individual subject variability. Then, we describe various methods for analyzing large-N datasets while accounting for the individual, including correlational analyses, machine learning, mixed-effects models, clustering, and simulation. We provide relevant examples of these techniques from published behavioral literature and from a publicly available dataset compiled from five different rat experiments, which illustrates both group-level effects and heterogeneity across individual subjects. We encourage other behavior analysts to make use of the substantial advancements in online data sharing to compile large-N datasets and use statistical approaches to explore individual differences.
Perspectives on Behavior Science, 2024 · doi:10.1007/s40614-023-00388-9