Multilevel modeling techniques, although used extensively in numerous
areas of social science research including demography, studies of scho
ol organization, and research on cognitive development, have been used
surprisingly infrequently in multisite evaluation studies. The goal o
f this article is to illustrate several ways in which multilevel model
ing techniques can help to broaden the kinds of questions that we are
able to address in multisite evaluations. In particular, it is shown h
ow these techniques provide a means of moving beyond estimating overal
l, average program effects to investigations of how differences in var
ious aspects of implementation across sites relate to differences in p
rogram success.