Individually randomized treatments are often administered within a group setting. As a consequence, outcomes for treated individuals may be correlated due to provider effects, common experiences within the group, and/or informal processes of socialization. In contrast, it is often reasonable to regard outcomes for control participants as independent, given that these individuals are not placed into groups. Although this kind of design is common in intervention research, the statistical models applied to evaluate the treatment effects are usually inconsistent with the resulting data structure, potentially leading to biased inferences. This article presents an alternative model that explicitly accounts for the fact that only treated participants are grouped. In addition to providing a useful test of the overall treatment effect, this approach also permits one to formally determine the extent to which treatment effects vary over treatment groups and whether there is evidence that individuals within treatment groups become similar to one another. This strategy is demonstrated with data from the Reconnecting Youth program for high school students at risk of school failure and behavioral disorders.Methods for analyzing data from randomized experiments have been widely disseminated for the case where the unit of randomization matches the unit to which treatment is administered. Approaches for analyzing data in which individuals are randomly assigned to individually administered treatments (e.g., individual therapy) are found in standard univariate and multivariate texts (e.g., Maxwell & Delaney, 2004;Neter, Kutner, Nachtsheim, & Wasserman, 1996). Approaches for analyzing data in which preexisting (intact) groups (e.g., clinics, classrooms, or neighborhoods) are randomly assigned to groupadministered treatments, as in cluster-randomized designs, are also readily available (see Murray & Blitstein, 2003;Raudenbush, 1997). These latter approaches account for lack of independence of observations within group to protect the nominal Type I error rate, either through adjustments of the test statistic and degrees of freedom (e.g., Baldwin, Murray, & Shadish, 2005) or by use of a mixed-effects (multilevel) model (e.g., Janega et al., 2004).A third type of design is also common in practice yet has received comparatively little methodological attention. Under this design, randomization to treatment is done on an individual basis; however, the treatment is administered in a group setting so that multiple Correspondence concerning this article should be addressed to Daniel J. Bauer, Department of Psychology, University of North Carolina, Chapel Hill, NC 27599-3270. dbauer@email.unc.edu.
NIH Public Access
Author ManuscriptMultivariate Behav Res. Author manuscript; available in PMC 2010 April 13.
NIH-PA Author ManuscriptNIH-PA Author Manuscript NIH-PA Author Manuscript individuals receive the treatment together. The groups are not preexisting but rather are formed by the investigator solely for the purpose of treatment provis...