MEPX
Chapter 7 of 10All chapters
  1. 1Samples and populations
  2. 2The central limit theorem
  3. 3Confidence intervals
  4. 4Hypothesis testing
  5. 5Multiple comparisons
  6. 6A/B testing
  7. 7Causal inference
  8. 8Regression
  9. 9A Bayesian view
  10. 10Reporting results

Chapter 7 of 10

Causal inference

When you cannot randomise.

Confounding

Observational comparisons mix the effect of the treatment with the reasons people received it. Adjustment helps and never fully substitutes for randomisation.

  • Adjusting for a variable on the causal path removes part of the real effect.
  • Draw the assumed causal diagram before choosing what to control for.

Quasi-experiments

Difference in differences, regression discontinuity and instrumental variables exploit near-random variation. Each rests on assumptions that should be stated and tested.