Causal Inference Tutorial

Define causal effects, defend comparison designs and test the assumptions behind intervention decisions.

Learning path

• Causal estimands: name the unit, treatment and missing counterfactual
• Confounders and covariate timing: adjust only for variables with a valid role
• Randomized assignment: check balance and retain every assigned unit
• Observational overlap and weighting: know where the data can compare
• Difference-in-differences: compare changes under a defended trend assumption
• Sensitivity and placebo checks: state how the causal claim could fail
• Project: review the effect of a new lesson recommendation panel

Connected foundations

Use the earlier data and model boundaries as prerequisites.

• Applied Statistics Tutorial
• Time Series Tutorial

Further paths

• Recommendation Systems Tutorial
• Data Visualization Tutorial

Practice

• Causal Inference: Projects

Continue into another subject: Online Experimentation Tutorial.