The Data Analyst's Guide to Cause and Effect

About the Authors Series Editor's Introduction Acknowledgments Chapter 1: Introduction The fundamental promise of causal inference Causal inference is "EEESI" The R programming language Formal notation Chapter objectives Further reading Chapter 2: Causal Graphs Randomizing a DAG Elementary ingredients of DAGs Good and bad controls Where do DAGs come from? Average people and people on average Chapter objectives Further reading Chapter 3: G-methods and Marginal Effects Inverse probability weighting G-computation It's assumptions all the way down Chapter objectives Further reading Chapter 4: Adventures in G-methods Doubly robust estimation Sub-group analysis Complex longitudinal designs Mediation analysis: Crossing hypothetical worlds Chapter objectives Further reading Chapter 5: Most of Your Data is Almost Always Missing External validity and selection bias Poststratification The treatment effects zoo Target populations and econometrics Chapter objectives Further reading Chapter 6: More Missing Data To be or not to be missing Completely random terminology Missing data imputation Chapter objectives Further reading Chapter 7: Multilevel modelling and Mundlak's legacy Causal inference as counterfactual prediction Mundlak models Marginal effects in a multilevel model Chapter objectives Further reading Chapter 8: Causal Inference is not Easy Violations of identification assumptions and some solutions Bayesian causal modelling Perspectives on RCT data analysis Causal inference in the era of Big Data and AI Conclusion References Index