Using multilevel modeling in large-scale planned variation educational experiments: Improving understanding of intervention effects

The author shows how one can combine a large-scale planned variation experi mental design and multilevel analysis to address research questions that go beyond the issue of overall treatment effectiveness. In particular, the de sign and analysis approach presented here can address the following researc h questions: how an educational intervention produces its results, for whom the intervention works, and whether the intervention works well across dif ferent contexts. The author used data based on a large-scale educational fi eld experiment to describe multilevel models that one can use to address th is set of research questions. Important design and analysis considerations are highlighted, especially with regard to assessing the impact of school-l evel characteristics.