This second edition of Design of Observational Studies is both an introduction to statistical inference in observational studies and a detailed discussion of the principles that guide the design of observational studies. An observational study is an empiric investigation of effects caused by treatments when randomized experimentation is unethical or infeasible. Observational studies are common in most fields that study the effects of treatments on people, including medicine, economics, epidemiology, education, psychology, political science and sociology. The quality and strength of evidence provided by an observational study is determined largely by its design. Design of Observational Studies is organized into five parts. Chapters 2, 3, and 5 of Part I cover concisely many of the ideas discussed in Rosenbaum’s Observational Studies (also published by Springer) but in a less technical fashion. Part II discusses the practical aspects of using propensity scores and other tools to create a matched comparison that balances many covariates, and includes an updated chapter on matching in R. In Part III, the concept of design sensitivity is used to appraise the relative ability of competing designs to distinguish treatment effects from biases due to unmeasured covariates. Part IV is new to this edition; it discusses evidence factors and the computerized construction of more than one comparison group. Part V discusses planning the analysis of an observational study, with particular reference to Sir Ronald Fisher’s striking advice for observational studies: "make your theories elaborate." This new edition features updated exploration of causal influence, with four new chapters, a new R package DOS2 designed as a companion for the book, and discussion of several of the latest matching packages for R. In particular, DOS2 allows readers to reproduce many analyses from Design of Observational Studies . From a review of the first edition:"Design of Observational Studies is a brilliantly written and thought-provoking book that should be read by every researcher who is involved in the design and analysis of observational studies. Part I is a general introduction to causal inference in observational studies. ... Two conceptual models of observational studies are discussed: a naive model assuming that individuals who look comparable are comparable and a more realistic model addressing the fact that individuals who look comparable for the observed covariates may differ in other ways." Giorgio Bedogni, Journal of the Royal Statistical Society, Series A 2011;174(1):244-5. From a review of the first edition:[Design of Observational Studies is] "a treasure of statistical history, philosophy, and principles for sound and creative study design that would benefit almost any statistician.Part III describes design sensitivity as a criterion for comparing different study designs paired with analytic approaches by the sensitivity of inferences to unmeasured biases." Peter B. Gilbert, Biometrics 2010;66:994-995. From a review of the first edition: "Design of Observational Studies gives a clear argument for the need for careful design of observational studies [with] particular attention paid ... to the choice of comparison subjects and design elements that can reduce unobserved confounding. Part II, Matching, goes into some detail on methods for matching on observed covariates, including propensity score matching ... optimal and full matching. Design of Observational Studies should be required reading for anyone planning or considering an observational study." Elizabeth Stuart, Journal of Educational and Behavioral Statistics 2010;35:774-778. From a review of the first edition:The book closes with ... an argument for the role of planning as ... the foundation of any analysis. A plan gives structure, prevents fishing, and guides transparency. ... Talk of overall plans raises several ideas not touched by many introductory texts such as detailed advice on how to handle multiple testing issues ... and a method for explicitly testing for equivalence rather than a stern lecture on how one cannot affirm the null. ... Design of Observational Studies deftly illustrates how cleverness and deep thinking about the particular problem at hand can result in some very nice and clean approaches to analyzing data. Luke Miratrix, Psychometrika 79, 540-542 (2014) From a review of the first edition: "Design of Observational Studies is an important book." Erkki P. Liski, International Statistical Review 2010;78:477-478 This second edition of Design of Observational Studies is both an introduction to statistical inference in observational studies and a detailed discussion of the principles that guide the design of observational studies. An observational study is an empiric investigation of effects caused by treatments when randomized experimentation is unethical or infeasible. Observational studies are common in most fields that study the e