Design of Observational Studies

Paul R. Rosenbaum is the Robert G. Putzel Professor of Statistics at the Wharton School of the University of Pennsylvania. He is a fellow of the American Statistical Association. In 2019, he received the R. A. Fisher Award, and in 2003 the George W. Snedecor Award, both from the Committee of Presidents of Statistical Societies (COPSS). He is the author of Observation and Experiment: An Introduction to Causal Inference (2017) and Observational Studies, 2nd edition (Springer 2002).

“References are listed after each chapter … reflecting the wealth of his contribution to the subject of causal inference over the last four decades. … The book is a comprehensive account of methods for comparing treatments in an observational study, rich with detailed illustrations using data for inferences of substance in education, epidemiology, economics and clinical medicine. … this is an absolute `must' for reading and reference for every statistician who works with observational studies … .” (Nicholas T. Longford, Mathematical Reviews, April, 2022)“This book is readily usable for self-study, a graduate seminar, or use by a practitioner getting their bearings in the field. The book is filled with references to both foundational work and cutting-edge approaches. … the book was an easy read. Rosenbaum provides practical advice, delivered in a conversational tone, and steers clear of theweeds that might bog a reader down in the main text. steers clear of the weeds that might bog a reader down in the main text.” (Sara Stoudt, MAA Reviews, July 24, 2021)

• Part I Beginnings.- 1 Dilemmas and Craftsmanship.- 2 Causal Inference in Randomized Experiments.- 3 Two Simple Models for Observational Studies.- 4 Competing Theories Structure Design.- 5 Opportunities, Devices, and Instruments.- 6 Transparency.- 7 Some Counterclaims Undermine Themselves.- Part II Matching.- 8 A Matched Observational Study.- 9 Basic Tools of Multivariate Matching.- 10 Various Practical Issues in Matching.- 11 Fine Balance.- 12 Matching Without Groups.- 13 Risk-Set Matching.- 14 Matching in R.- Part III Design Sensitivity.- 15 The Power of a Sensitivity Analysis and Its Limit.- 16 Heterogeneity and Causality.- 17 Uncommon but Dramatic Responses to Treatment.- 18 Anticipated and Discovered Patterns of Response.- 19 Choice of Test Statistic.- Part IV Enhanced Design.- 20 Evidence Factors.- 21 Constructing Several Comparison Groups.- Part V Planning Analysis.- 22 After Matching, Before Analysis.- 23 Planning the Analysis.- Summary: Key Elements of Design.- Solutions to Common Problems.- Symbols.- Acronyms.- Glossary of Statistical Terms.- Further Reading.- Suggested Readings for a Course.- Index.