Research Design in the Social Sciences

Graeme Blair is associate professor of political science at the University of California, Los Angeles. Alexander Coppock is associate professor of political science at Yale University. Macartan Humphreys is professor of political science at Columbia University and director of the Institutions and Political Inequality group at the WZB Berlin Social Science Center.

• AcknowledgementsPart I Introduction1 Preamble1.1 How to Read This Book1.2 How to Work This Book1.3 What This Book Will Not Do2 What Is a Research Design?2.1 MIDA: The Four Elements of a Research Design2.2 Declaration, Diagnosis, Redesign2.3 Example: A Decision Problem2.4 Putting Designs to Use3 Research Design Principles4 Getting Started4.1 Installing R4.2 Declaration4.3 Diagnosis4.4 Redesign4.5 Library of Designs4.6 Long-Term Code UsabilityPart II Declaration, Diagnosis, Redesign5 Declaring Designs5.1 Definition of Research Designs5.2 Declaration in Code6 Specifying the Model6.1 Elements of Models6.2 Types of Variables in Models6.3 How to Specify Models6.4 Summary7 Defining the Inquiry7.1 Elements of Inquiries7.2 Types of Inquiries7.3 How to Define Inquiries7.4 Summary8 Crafting a Data Strategy8.1 Elements of Data Strategies8.2 How to Craft Data Strategies8.3 Summary9 Choosing an Answer Strategy9.1 Elements of Answer Strategies9.2 Types of Answer Strategies9.3 How to Choose an Answer Strategy9.4 Summary10 Diagnosing Designs10.1 Elements of Diagnoses10.2 Types of Diagnosands10.3 Estimation of Diagnosands10.4 How to Diagnose Designs10.5 Summary11 Redesigning11.1 Redesigning over Data Strategies11.2 Redesigning over Answer Strategies11.3 Summary12 Design Example12.1 Declaration in Words12.2 Declaration in Code12.3 Diagnosis12.4 Redesign13 Designing in Code13.1 Model13.2 Inquiry13.3 Data Strategy13.4 Answer Strategy13.5 Declaration13.6 Diagnosis13.7 RedesignPart III Research Design Library14 Research Design Library15 Observational: Descriptive15.1 Simple Random Sampling15.2 Cluster Random Sampling15.3 Multilevel Regression and Poststratification15.4 Index Creation16 Observational: Causal16.1 Process Tracing16.2 Selection-on-Observables16.3 Difference-in-Differences16.4 Instrumental Variables16.5 Regression Discontinuity Designs17 Experimental: Descriptive17.1 Audit Experiments17.2 List Experiments17.3 Conjoint Experiments17.4 Behavioral Games18 Experimental: Causal18.1 Two-Arm Randomized Experiments18.2 Block-Randomized Experiments18.3 Cluster-Randomized Experiments18.4 Subgroup Designs18.5 Factorial Experiments18.6 Encouragement Designs18.7 Placebo-Controlled Experiments18.8 Stepped-Wedge Experiments18.9 Randomized Saturation Experiments18.10 Experiments over Networks19 Complex Designs19.1 Discovery Using Causal Forests19.2 Structural Estimation19.3 Meta-analysis19.4 Multi-site StudiesPart IV Research Design Lifecycle20 Research Design Lifecycle21 Planning21.1 Ethics21.2 Partners21.3 Funding21.4 Piloting21.5 Criticism21.6 Preanalysis Plan22 Realization22.1 Pivoting22.2 Populated Preanalysis Plan22.3 Reconciliation22.4 Writing23 Integration23.1 Communicating23.2 Archiving23.3 Reanalysis23.4 Replication23.5 Meta-analysisPart V Epilogue24 EpiloguePart VI ReferencesBibliographyIndex

"Winner of the Best Book Award, Experiments Section of the American Political Science Association"