Between-case standardized effect size analysis of single case designs: Examination of the two methods.

Stephens et al. (2018) built two new ways to measure how big an effect is in single-case work. Both methods give one number that compares the treated phase to the baseline phase across different participants.

They checked if these numbers lined up with what earlier big reviews already said about which interventions work best.

The two new metrics sorted strong and weak treatments in the same order as the old reviews. This means the tools can tell a good intervention from a poor one.

The catch: the metrics do not behave the same in every design, so you have to pick the right one for your study shape.

Howard et al. (2019) later showed that one of these metrics, BC-SMD, matches expert eyeball judgment better than most rivals. Together the papers give you both a number and a check that the number makes sense.

Manolov et al. (2022) took the idea further. They built a free plot that uses your BC-SMD values to show if effects repeat across kids, turning the single number into a visual replication tool.

Dowdy et al. (2025) went even bigger. They feed BC-SMD-style effects into a live Bayesian system that pools data from many labs as soon as each new case finishes, so you no longer have to wait years for enough replications.

If you run or read single-case studies, these tools let you speak the same language as meta-analysts and journal reviewers. Compute BC-SMD or its twin, drop the value into the free Manolov plot, and you can show strong, replicable evidence in one figure. Start now: add the BC-SMD sheet to your next multiple-baseline project and watch your visual story get a numeric backbone.