Project Goals

The overall goal of EASI is to provide for the rapid creation of deployment of experiments in educational technologies.

• A–Design: Help researchers investigate theories of learning and discover how to improve instruction by designing randomized field experiments on components of real-world digital educational resources.
• B–Analysis: Facilitate sophisticated analysis of experiments in the context of large-scale data about student profiles, such as to discover which interventions are effective for different subgroups of students.
• C–Adaptation: Enable research into adaptive experimentation by providing a testbed for algorithms that dynamically analyze data from experiments, to enhance learning faster with less participants

Why EASI? Run your Experiment View on UpGrade

Why it matters

• Run randomized and adaptive experiments (Thompson sampling & Bayesian inference) to get answers with fewer participants.
• Monitor results in real time with dashboards and alerts.
• Keep experiments reproducible with versioned configs and analysis pipelines.
• Integrate easily with analytics, LMS, and CI for production workflows.

A concrete win: well‑designed experiments have shown small instructional tweaks can raise outcomes substantially — for example, prompting students to reflect on course relevance improved performance by roughly half a letter grade (Hulleman & Harackiewicz, 2009).¹

How it works

1. Design: author alternative instructional versions and an experiment config.
2. Deploy: route users and run adaptive allocation in production.
3. Learn: visualize outcomes, adapt or declare winners, and export reproducible analyses.