The Compound Multiple-Baseline Design.

Abstract

The multiple-baseline design is a predominant experimental design in applied behavior-analytic research. Despite its strengths, when baseline lengths are assigned a priori, it is possible that the independent variable may be implemented when baseline data are trending in the same direction that is anticipated for positive treatment outcomes, thus threatening experimental control. A partial solution to this problem is to modify the traditional multiple-baseline design and stagger baselines across more than one dimension (e.g., across both individuals and settings). The purpose of this article is to describe the historical underpinnings of this approach, to highlight more recent uses of the design, and to emphasize possible areas suitable for application.