An Evaluation of Analysis Options for the One-Group-Per-Condition Design

Abstract

This article addresses the analytic problems associated with a design in which one identifiable group is allocated to each treatment condition and members of those groups are measured to assess the intervention. Such designs are often called quasi-experiments if the groups are not randomized to conditions and group-randomized trials if the groups are randomized. They present special problems, and previous reports have argued against their use in efficacy or effectiveness trials. Even so, this design still appears with surprising frequency. This article presents the results from a new simulation study that underscores the analytic problems associated with this design.