Transition States in Single Case Experimental Designs.
Expect the old behavior pattern to stick around for about five data points in roughly one out of every 14 single-case studies.
01Research in Context
What this study did
The authors looked at 1,400 single-case graphs from published studies. They counted how many showed a "transition state" — a short run where the new phase starts but the old pattern keeps going.
They wanted to know how often this lag happens and how long it lasts.
What they found
About 1 in every 14 graphs had this leftover baseline pattern. The hangover lasted about five data points before the real treatment effect showed up.
If you stop measuring too soon, you might call the intervention a failure when it just needs a few more sessions.
How this fits with other research
Laureano et al. (2023) saw the same thing in hospital files, but found it only 3% of the time. The gap comes from where the data lived — journals versus clinical charts — not from a true clash.
Killeen (1978) gave us old-school rules for deciding when behavior is "stable." The new count of transition states adds a warning: even after your rule says "go," the old pattern can linger for a handful of points.
Elliffe et al. (2019) handed us a free trend test that works with unequal phase lengths. You can plug their test into these laggy first points to see if change has really started.
Why it matters
Next time you run a single-case study, keep measuring for a few extra sessions after the phase line. If you see the old trend hang on, wait — it may flip soon. Share this heads-up with journal reviewers who expect instant change; it keeps good interventions from getting tossed too early.
Get CEUs on This Topic — Free
The ABA Clubhouse has 60+ on-demand CEUs including ethics, supervision, and clinical topics like this one. Plus a new live CEU every Wednesday.
Add at least five more data points after your phase change before you judge if the intervention is working.
02At a glance
03Original abstract
The continuation of a baseline pattern of responding into a treatment phase, sometimes referred to as a "transition state," can obscure interpretation of data depicted in single-case experimental designs (SCEDs). For example, when using visual analysis, transition states may lead to the conclusion that the treatment is ineffective. Likewise, the inclusion of overlapping data points in some statistical analyses may lead to conclusions that the treatment had a small effect size and give rise to publication bias. This study reviewed 20 volumes in a journal that publishes primarily SCEDs studies. We defined a transition state as a situation wherein at least the first three consecutive data points of a treatment phase or condition are within the range of the baseline phase or condition. Results indicate that transitions states (a) were present for 7.4% of graphs that met inclusion criteria and (b) occurred for a mean of 4.9 data points before leading to behavior change. We discuss some implications and directions for future research on transition states.
Behavior modification, 2023 · doi:10.1177/0145445519839213