3 credits
Fall 2026 Lecture Upper Division
Causal questions arise across science, policy, business, and technology, yet answering them from data requires more than standard predictive methods. This course introduces causal inference, focusing on how researchers can define causal effects, understand the assumptions behind identification, and estimate causal quantities from experimental and observational data. The course moves from foundational ideas to modern challenges, including heterogeneous effects, longitudinal treatments, network interference, and machine learning based methods. With emphasis placed on both methodological rigor and practical relevance, the course is designed for students in statistics, computer science, economics, social sciences, public health, and related fields who want a broad introduction to modern causal inference.
Learning Outcomes1Define and identify causal effects in randomized and observational studies using the causal frameworks.
2Apply core methods for estimating causal effects and assess their strengths, limitations, and required assumptions.
3Analyze causal questions in modern data settings and evaluate how machine learning can support causal inference.
Prerequisites
Restrictions
made by Purdue students.