Neyman causal inference framework distinguishing finite-population and super-population models for clustered education RCTs¶

Theory · All theories
Evidence · no claims cited

Description¶

The report grounds the estimation of average treatment effects in two-stage clustered RCTs in the Neyman causal inference framework. Its key organizing distinction is whether potential treatment and control group outcomes are "considered to be fixed for the study population (the finite-population model) or randomly selected from a vaguely defined universe (the super-population model)". Appropriate estimators are derived and discussed for each model.

Design Implications¶

Context¶

Requirements¶

• Analysts must choose between the finite-population and super-population causal models, since the appropriate estimators differ by model

Constraints¶

• The framework is developed for two-stage clustered randomized controlled trial designs in education research

Target Learners¶

• students in education interventions evaluated through clustered RCTs

Target Learning Objectives¶

• accurate estimation of average treatment effects of education interventions

Claims¶

Related Theories¶

• A loss function approach grounded in the causal inference literature for evaluating late pretest use in RCTs

Examples¶

-

Key Sources¶

• Peter Z. Schochet. (2009). Technical Methods Report: The Estimation of Average Treatment Effects for Clustered RCTs of Education Interventions. Washington, DC: National Center for Education Evaluation and Regional Assistance, Institute of Education Sciences, U.S. Department of Education. https://ies.ed.gov/ncee/