Drug prevention programs, for example, seek to reduce drug use by increasing skills to resist drug offers and engendering norms less tolerant of drug use. AIDS and sexually transmitted disease prevention programs are designed to increase safer sex practices and to reduce infection. The success of prevention and intervention programs is determined by their effects on such outcome variables as drug use, death, and disease. Mediation analysis can facilitate program evaluation by identifying why programs work or fail to work. Because most prevention studies measure mediating constructs, mediation effects can be assessed on many existing datasets. Several computer programs involving covariance structure analysis are available that compute standard errors of mediated effects. The measurement of mediation is described in terms of point and interval estimation and mediation when the dependent variable is categorical. Mediation methods are applied to a cholesterol reduction program and a school-based drug prevention program. 31 references