/ Single-Case Design Graphs

Overview › Design guide › Multiple baseline

Design guide

Multiple baseline and multiple probe designs

Start the intervention at different times across three or more participants, behaviors, or settings. If each one changes only when its own intervention begins, the intervention is responsible.

You will be able to

  • Explain how staggered starts across three or more tiers give three demonstrations of the effect.
  • Check a multiple baseline or multiple probe design against the WWC minimums and the probe rules.
  • Decide whether multiple baseline graphs show experimental control, and say why when they don't, reaching 8 of your last 10 in the practice.
Question it answersDoes behavior change only when, and only where, the intervention is introduced?
Use it whenThe behavior won't reverse or withdrawal isn't acceptable, and you have three or more similar but independent tiers.
Avoid it whenTreating one tier is likely to change the others, or the later tiers can't wait in baseline.

How it shows control

All tiers start in baseline together. When the first tier begins intervention, the tiers still in baseline act as controls. If they stay stable while the first tier changes, that verifies that time alone isn't producing change. Each staggered start then replicates the effect. Three tiers give three demonstrations at three different times.

The logic of this design in more depth, its judgment calls and exceptions, and a knowledge check: Visual analysis Lesson 3, Part C.

Minimum standards

What experimental control looks like

Experimental control Three-tier multiple baseline graph of percentage correct. Baselines last 5, 8, and 11 sessions, with data between 7 and 23 percent. Each participant's data rise to 40 percent in the first intervention session and reach 94 to 99 percent, only after that participant's intervention begins.
Each tier changes only when it is treated. Participants 2 and 3 stay stable while Participant 1 improves. Each changes right after its own start, giving three demonstrations.

What it doesn't look like

Untreated tiers changed Three-tier multiple baseline graph of percentage correct. All baselines are between 8 and 23 percent for the first 5 sessions. At session 6, when Participant 1 starts intervention, Participants 2 and 3 rise to about 50 percent while still in baseline and keep rising to 74 and 84 percent before their own interventions begin.
Covariation. When Participant 1 began intervention, Participants 2 and 3 improved too, while still in baseline. Something else changed for everyone, or the participants influenced each other. The staggered starts no longer separate the intervention from time.
Only two demonstrations Three-tier multiple baseline graph of percentage correct. Participants 1 and 2 rise from below 25 percent to above 90 percent after their interventions begin. Participant 3 stays between 7 and 21 percent before and after intervention begins at session 12.
One tier didn't respond. Participants 1 and 2 changed, but Participant 3 didn't. Two demonstrations fall short of the three needed, and the non-effect weakens the evidence.
Baseline trend Three-tier multiple baseline graph of percentage correct. Every participant improves steadily from session 1, about 4 to 5 points per session, at the same rate before and after their own intervention begins. Participant 1 rises from 13 to 31 percent in baseline and from 35 to 90 percent in intervention, Participant 2 from 18 to 46 percent and from 51 to 88 percent, and Participant 3 from 7 to 58 percent and from 62 to 91 percent.
Already improving everywhere. All three participants improved from the first session. From each participant's last baseline session to their first intervention session, the data rose only 4 or 5 points, about their average climb per session. The changes don't line up with the staggered starts, so they can't be credited to the intervention.

Multiple probe design

When measuring every tier in every session is impractical or reactive, use intermittent probes in baseline. Reactive means testing itself teaches or tires the participant. Before a tier begins intervention, it gets several consecutive probes. These show that its baseline is still stable at the moment the intervention starts. The logic of control is the same as for a multiple baseline (Horner & Baer, 1978).

Minimum standards for multiple probe

The 2010 WWC pilot standards don't mention multiple probe designs. A later WWC handbook added three probe rules on top of the multiple baseline minimums (What Works Clearinghouse, 2017, pp. A-5 to A-6):

If a tier has at least one probe in each of those three-session windows, but not three in a row, the study can still meet the standards with reservations. A study that has no probe in one of those windows, or skips the probe when another tier starts, does not meet them.

Experimental control Multiple probe graph with three skill sets. All three are probed in sessions 1 to 3, the sets still in baseline are probed again when another set starts teaching, and each set gets three consecutive probes before its own teaching starts. Each set improves only after its teaching begins.
Probes instead of continuous baseline. All three skill sets are probed in the first three sessions. Each set still in baseline is probed again when another set starts teaching, and in three consecutive sessions just before its own teaching starts. Each set changes only once it is taught.

Practice

Decide whether each graph shows experimental control. When it doesn't, also choose why. An item counts only when both answers are right.

Graph it