This article proposes and evaluates a method to test for mediation in multi
level data sets formed when an intervention administered to intact groups i
s designed to produce change in individual mediator and outcome variables.
Simulated data of this form were used to compare ordinary least squares (OL
S) and two multilevel estimators of the mediated effect. OLS and multilevel
standard error approximations were also evaluated and recommendations give
n for optimal estimator choice. These methods were applied to data from an
existing substance use intervention to show the impact multilevel mediation
modeling can have on the conclusions drawn from real-world evaluation stud
ies.