Some statistical treatments compatible with individual organism methodology.
Four clients, daily coin flips, and a simple ANOVA give you a publishable p-value while keeping single-subject control.
01Research in Context
What this study did
Revusky (1967) built a new way to run stats on one-person experiments. Four people are enough if you flip a coin each day to decide who gets the treatment that day.
The others stay in baseline. After a few weeks you can hit p < 0.05 without big groups.
What they found
The math works. Random swaps inside each person give the same power as a big between-group study.
You keep full control and still get a clean p-value.
How this fits with other research
Michael (1974) says skip the p-value. Strong visuals and steady control speak louder than any test.
Campbell (2004), Sen (2022), and DeHart et al. (2019) moved past yes-no tests. They give effect sizes, mixed models, and regression tools that meta-analysts can pool.
These newer papers do not say Revusky (1967) is wrong. They just offer richer ways to tell how big an effect is, not only if it exists.
Why it matters
If you run brief consultations or small clinics, you can still test an intervention with four clients. Randomly assign the treatment days, graph the data, and report the p-value. Pair this with a modern effect size from Campbell (2004) or DeHart et al. (2019) and you satisfy both old and new camps.
Want CEUs on This Topic?
The ABA Clubhouse has 60+ free CEUs — live every Wednesday. Ethics, supervision & clinical topics.
Join Free →Pick four clients, flip a coin each day to choose who gets treatment, and plot the data — you can test significance after two weeks.
02At a glance
03Original abstract
Consider experimental treatments with consequences so irreversible that baseline performance cannot be recovered. The conventional method of assessing the effects of such treatments by statistical means involves separate experimental and control groups. An alternative proposed here is to administer the experimental treatment to each subject, one subject at a time and in a random order; whenever any subject receives the experimental treatment, those subjects which have not yet received it receive a control treatment. This procedure permits results significant at the one-tailed 0.05 level to be obtained with four subjects; if a two-group procedure evaluated by means of the U test is used, a minimum of six subjects is needed for the same significance level. More generally, the procedure permits equal sensitivity to any experimental effect with over 30% fewer subjects than a two-group procedure. Extensions of the basic method are made to a variety of levels of the experimental treatment and to treatments without irreversible effects, and limitations of the method are discussed.
Journal of the experimental analysis of behavior, 1967 · doi:10.1901/jeab.1967.10-319