Lesson 2 · Causal Inference · Step 2 of 6
The road not taken
A causal effect is a difference between two outcomes for the same person — what happened with the treatment, and what would have happened without it. Only one of those ever occurs. That is the fundamental problem of causal inference: the counterfactual is missing by definition, for everyone, always. We get around it by comparing groups rather than individuals, which works only if the groups stand in for each other's missing halves. When they do not, the difference you measure is selection, not effect.
Also covered: potential outcomes · counterfactuals · average treatment effect · selection bias
Alongside this step
- Slides and transcript — the whole video
- Read the chapter — Causal Inference
Lesson 2 · 6 steps
The Validity Toolkit · lesson 2 of 4