Using data from the evaluation of the Fast Track intervention, this article illustrates three methods for handling attrition. Multiple imputation and ignorable maximum likelihood estimation produce estimates that are similar to those based on listwise-deleted data. A panel selection model that allows for selective dropout reveals that highly aggressive boys accumulate in the treatment group over time and produces a larger estimate of treatment effect. In contrast, this model produces a smaller treatment effect for girls. The article's conclusion discusses the strengths and weaknesses of the alternative approaches and outlines ways in which researchers might improve their handling of attrition.
Keywordsattrition; imputation; selection models; nonresponse When asked, many program evaluators likely will name attrition as one of the greater threats to evaluation. 1 The deleterious effects are several. First, even under the best of conditions, attrition likely reduces the statistical power of the analyses of the available data (Orr 1999 ).2 In addition, attrition may compromise the external validity of the study, especially in those circumstances in which the likelihood of response is related to observed characteristics, such as race or place of residence. In those instances, the resulting parameter estimates may generalize only to a subset of the population of interest (Orr 1999). Suppose, for example, that all African American participants drop out of an evaluation. In that instance, the study's findings likely generalize only to the remaining racial and ethnic groups in the study. This example is extreme; one generally does not lose all individuals of a given race or ethnicity (or of any subgroup, unless it is very narrowly defined). Rather, attrition is often linked to a range of Correspondence concerning this article should be addressed to E. Michael Foster, Pennsylvania State University, 159 Henderson Building South, University Park, PA 16802-6500. For additional information concerning Fast Track, see http://www.fasttrackproject.org. Conduct Problems Prevention Research Group members include, in alphabetical order, Karen L. Bierman, Department of Psychology, Pennsylvania State University; John D. Coie, Department of Psychology, Duke University; Kenneth A. Dodge, Center for Child and Family Policy, Duke University; E. Michael Foster, Department of Health Policy and Administration, Pennsylvania State University; Mark T. Greenberg, Department of Human Development and Family Studies, Pennsylvania State University; John E. Lochman, Department of Psychology, University of Alabama; Robert J. McMahon, Department of Psychology, University of Washington; and Ellen E. Pinderhughes. Department of Child Development, Tufts University 1 Note that this article addresses dropout from the evaluation rather than from the intervention itself. The empirical example represents an intention-to-treat analysis. 2 Power is often reduced but not in every case; power might be improved if the most extreme (and least predictable) o...