Between Subjects Design

What is a between subjects design?

A between subjects design, also called an independent groups or between-groups design, compares different participants in different conditions. One group experiences one condition; another group experiences another. The outcomes are then compared.

In a randomized experiment, participants are randomly assigned to groups. A design can also be between subjects without random assignment, as in a comparison of existing groups. That distinction matters when deciding what caused a difference.

Examples of between subjects design

• Pharmaceutical trial: one group receives a study medication and another receives a placebo; researchers compare a specified outcome.
• Marketing study: one group sees Ad A and another sees Ad B; purchasing or attitudes are measured.
• Educational study: different groups receive different teaching methods; researchers compare learning outcomes.

These are possible study arrangements, not results. Assignment, measurement, attrition, and analysis affect the strength of a causal conclusion.

Advantages and limitations

Participants do not carry experience of one experimental condition into the other. That can be useful when a treatment or learning task has effects that cannot be reversed.

The tradeoff is variation between people. Random assignment does not make the groups exactly equal in a particular sample. Baseline measures, blocking, or suitable matching can improve precision. A between subjects study may also need more participants than a comparable within-subjects study, depending on the variation and the design.

With nonrandomized groups, pre-existing differences can threaten a causal interpretation. Adding a pretest alone does not remove every confound.

Source

Campbell and Stanley’s design text distinguishes randomized experiments from nonrandomized comparisons.