Developing statistical methods to obtain estimates of systematic variation in the effects of educational practices across places and population subgroups
Sean Reardon leads this work with funding from the William T. Grant Foundation. This work was previously supported by the AERA research grants program.
In educational research, it is often not enough to know that a particular practice is, on average, effective—more important, perhaps, is to understand the conditions under which, and populations for whom, a particular practice or policy has positive effects. Reardon’s substantive work in this area focuses on understanding whether and how neighborhood social conditions moderate the effect of school and family interventions aimed at improving achievement, and on understanding the extent to which Catholic schooling effects vary across educational markets.
More generally, this work is concerned with developing a set of methodological tools (based on combining a site-clustered matching estimator with multilevel modeling and meta-analysis) to enable educational researchers to design studies that will allow them to extend research from answering questions about “what works” to answer questions about “what works for whom, and under what circumstances.”