Low-Cost Randomized Controlled Trials in Education
- (pp. 307-11)
AbstractRandomized controlled trials (RCTs) are widely accepted as the gold standard in program evaluation but are uncommon in educational research. A likely explanation is that experiments designed with sufficient statistical precision to detect meaningful impacts of educational interventions generally require resources unobtainable for most studies. This paper proposes an alternative RCT design, where treatment status varies by lesson. We show that this design plausibly enables the precise estimation of causal impacts of a broad class of educational interventions with modest resources.
CitationWozny, Nathan, Cary Balser, and Drew Ives. 2018. "Low-Cost Randomized Controlled Trials in Education." AEA Papers and Proceedings, 108: 307-11. DOI: 10.1257/pandp.20181054
- C93 Field Experiments
- I23 Higher Education; Research Institutions