First Course in Causal Inference

Peng Ding is an Associate Professor in the Department of Statistics at UC Berkeley. His research focuses on causal inference and its applications.

"Written by a rising star in the field and refined through its use in several advanced undergraduate and first-year graduate-level courses, A First Course in Causal Inference is an excellent textbook that fulfills its stated purpose. [...] An introductory text must balance breadth and depth. The author ambitiously covers a broad range of topics, from fundamental concepts in randomization inference and observational studies to more advanced subjects such as sensitivity analysis, instrumental variables, and mediation analysis, all within 400 pages. [...]. Overall, this textbook is highly recommended for advanced undergraduate and first-year graduate courses. It provides students with a solid foundation in causal inference, equipping those with a typical statistical background but no prior exposure to causal inference with the necessary tools for application and further research."-Kwun Chuen Gary Chan in The American Statistician, September 2025"Overall I am pleased to see "A First Course in Causal Inference" by Peng Ding in press. Ding should be commended on a wonderfully useful textbook. I would heartily recommend it to instructors teaching a causal inference course in a statistics department, and am excited to continue to put it to use myself."-Nicole E. Pashley in Observational Studies, June 2025"This book offers a statistician’s perspective on causal inference. It provides an invaluable review of statistical paradoxes in causal inference from observational data, linking those paradoxes to Pearl’s directed acyclic graphs (DAGs). The overview of the literature on matching is the best that I’ve seen, and the inclusion of R code is a huge plus. The book would make a great introduction (and more) to advanced undergraduate and masters programs in statistics."-Professor Bryan Dowd, University of Minneapolis, U.S.A."A First Course in Causal Inference by Peng Ding is written by an authority in the field at technical level that makes it stand out from existing textbooks on causal inference. It will be a welcome resource for students and researchers in public health, medicine, and the social sciences who have a good background in math and statistics. Exercises lead readers through important results, appendices review key mathematical and statistical concepts, and the book contains well-written R code that will be extremely useful for translating theory into practice."-Professor Eben Kenah, The Ohio State University, U.S.A."Professor Ding accomplished something impressive with this book — a clear, precise, and thorough introduction to Causal Inference. This book is a must-have for anyone interested in understanding the subject. I highly recommend it."-Professor Hugo Jales, Syracuse University, Maxwell School of Citizenship & Public Affairs, USA.

• PrefacePart 1: Introduction 1. Correlation, Association, and the Yule–Simpson Paradox2. Potential OutcomesPart 2: Randomized experiments 3. The Completely Randomized Experiment and the Fisher Randomization Test4. Neymanian Repeated Sampling Inference in Completely Randomized Experiments5. Stratification and Post-Stratification in Randomized Experiments6. Rerandomization and Regression Adjustment7. Matched-Pairs Experiment8. Unification of the Fisherian and Neymanian Inferences in Randomized Experiments9. Bridging Finite and Super Population Causal InferencePart 3: Observational studies 10. Observational Studies, Selection Bias, and Nonparametric Identification of Causal Effects11. The Central Role of the Propensity Score in Observational Studies for Causal Effects12. The Doubly Robust or the Augmented Inverse Propensity Score Weighting Estimator for the Average Causal Effect13. The Average Causal Effect on the Treated Units and Other Estimands14. Using the Propensity Score in Regressions for Causal Effects15. Matching in Observational StudiesPart 4: Difficulties and challenges of observational studies 16. Difficulties of Unconfoundedness in Observational Studies for Causal Effects17. E-Value: Evidence for Causation in Observational Studies with Unmeasured Confounding18. Sensitivity Analysis for the Average Causal Effect with Unmeasured Confounding19. Rosenbaum-Style p-Values for Matched Observational Studies with Unmeasured Confounding20. Overlap in Observational Studies: Difficulties and OpportunitiesPart 5: Instrumental variables 21. An Experimental Perspective of the Instrumental Variable22. Disentangle Mixture Distributions and Instrumental Variable Inequalities23. An Econometric Perspective of the Instrumental Variable24. Application of the Instrumental Variable Method: Fuzzy Regression Discontinuity25. Application of the Instrumental Variable Method: Mendelian RandomizationPart 6: Causal Mechanisms with Post-Treatment Variables 26. Principal Stratification27. Mediation Analysis: Natural Direct and Indirect Effects28. Controlled Direct Effect29. Time-Varying Treatment and ConfoundingPart 7: Appendices A. Probability and StatisticsB. Linear and Logistic RegressionsC. Some Useful Lemmas for Simple Random Sampling From a Finite Population