Machine Learning Guided Program Evaluation

Open to PhD students and faculty engaged in causal inference in education research.

About CIERS:

The objective of the Causal Inference in Education Research Seminar (CIERS) is to engage students and faculty from across the university in conversations around education research using various research methodologies. This seminar provides a space for doctoral students and faculty from the School of Education, Ford School of Public Policy, and the Departments of Economics, Sociology, Statistics, and Political Science to discuss current research and receive feedback on works-in-progress. Discourse between these schools and departments creates a more complete community of education scholars, and provides a networking opportunity for students enrolled in a variety of academic programs who share common research interests. Open to PhD students and faculty engaged in causal inference in education research.

Abstract:

Many causal inference strategies, particularly regression discontinuity, rely on knowing exact treatment assignment processes to identify subjects who are plausibly exogenously given treatment. We use machine learning (ML) methods to first identify these marginal individuals, before relying on regression discontinuity to estimate treatment effects. Our approach differs from directly using ML to create an estimator as in most of the literature. We apply our strategy to evaluate a college program designed for under-prepared students. At this program at a large public flagship, students enter a pre-enrollment summer program to give under-prepared students skills needed to perform at level with their peers. Since students are simultaneously told their admission and program designation, we first study effects on subsequent enrollment. Our preliminary results suggest this program boosts subsequent enrollment.

This is a joint paper with Bill Gehring and Wei Ai.

• program evaluation
• regression
• Machine Learning