crossover design
a study in which different treatments are applied to the same individuals but in different sequences. In the most basic crossover design, a group of participants receives Treatment A followed by Treatment B whereas a second group receives Treatment B followed by Treatment A. For example, a researcher could use such a design to assess the effect of attending a day service on stroke survivors, randomly assigning participants to one of two groups, the first of which would attend the service for 6 months and then not attend for 6 months, and the second of which would not attend the service for 6 months and then would attend for 6 months. As with within-subjects designs, the benefit of this design is the reduction in error variance. Also called crossover study; crossover trial. Compare parallel-groups design. See also Graeco-Latin square; Latin square.