Led by Wei Li

Building rigorous evidence for education decisions

The Longitudinal Causal Data Science Lab is directed by Wei Li, Associate Professor in Research and Evaluation Methodology at the University of Florida and NSF CAREER Awardee. Our work connects statistical methodology, causal evaluation, education data science, AI, and applied partnerships.

We develop statistical methods, software, and applied partnerships that help education researchers design longitudinal studies, estimate causal effects, understand who benefits, and connect impact evidence to cost, implementation, and scale.

Research Focus Areas

Four ways we build stronger evidence

Longitudinal Design, Power, and Optimal Study Planning

We develop design parameters, power methods, and sample-size tools for longitudinal, multilevel, and repeated-measures studies.

Causal Evaluation and Heterogeneous Treatment Effects

We study experimental and quasi-experimental methods, staggered difference-in-differences, mediation, moderation, and machine learning for heterogeneous effects.

Education Data Science, AI, and Digital Learning Systems

We use large-scale administrative, digital learning, assessment, and AI-enabled data systems to generate interpretable evidence.

Intervention Evaluation, Cost-Effectiveness, and Implementation Evidence

We connect impact estimates with cost, implementation, scalability, and decision-making for education programs.

News

Lab updates