Causal Mediation Analysis: (Analytical Methods for Social Research)

Geoffrey T. Wodtke and Xiang Zhou's Causal Mediation Analysis offer a comprehensive yet accessible guide to causal mediation analysis for social scientists. They explore why an exposure affects an outcome by quantifying the processes and mechanisms through which a causal effect operates. Covering everything from traditional methods through machine learning techniques and experimental designs for analysing mediation, the authors make these methods broadly accessible through clear explanations, practical examples, and the inclusion of extensive Stata and R code, allowing readers to replicate all the empirical illustrations and apply the methods directly to their own data. Starting with methods for intuitive, simple settings, they build up to more complex analyses, ensuring a smooth learning experience. Rich in examples from across sociology, psychology, political science, and economics, the authors demonstrate the application of cutting-edge methods to real-world empirical research, providing practical tools and examples for rigorous empirical research across disciplines.

Table of Contents:
1. Introduction; 2. Foundations of causal inference; 3. Mediation analysis with baseline confounding; 4. Mediation analysis with exposure-induced confounding; 5. Mediation analysis with multiple mediators; 6. Mediation analysis with robust estimation methods; 7. Mediation analysis with (Quasi-)experimental methods; 8. The future of causal mediation analysis.

About the Author :
Geoffrey T. Wodtke is a Professor in the Department of Sociology and Committee on Quantitative Methods in Social, Behavioral, and Health Research at the University of Chicago. He is the winner of the 2020 Leo Goodman Award for contributions to sociological methodology from the American Sociological Association. He earned his Ph.D. in sociology from the University of Michigan in 2014, where he also received an MA in statistics. Xiang Zhou is Professor of Sociology at Harvard University, where he is also affiliated with the Institute for Quantitative Social Science and the Harvard Data Science Initiative. He is the winner of the 2022 Leo Goodman Award for contributions to sociological methodology from the American Sociological Association. He earned his PhD in sociology and statistics from the University of Michigan in 2015.

Review :
'This book offers a modern view of mediation analysis from the causal inference perspective. It reviews rigorous statistical causal inference theory and methods for mediation analysis. Moreover, it also provides clear motivations and applications of mediation analysis from social sciences. It will soon become a canonical reference for applied researchers who will use mediation analysis for data analysis, and for theoretical researchers who will develop novel statistical methods related to mediation analysis.' Peng Ding, Department of Statistics, University of California Berkeley 'You don't need to learn about causal mediation – as long as you're also ok abandoning a central goal of social science research. Otherwise, you couldn't find a better guide to the fast progress in this field than Wodtke and Zhou's engaging new book.' Gary King, Albert J Weatherhead III University Professor, Harvard University 'Wodtke and Zhou are leaders in causal analysis. This book, Causal Mediation Analysis, is a masterfully written, highly accessible and deeply insightful guide to one of the most important tools in social science research. It is sure to become a go-to resource for social and behavioral researchers seeking to uncover causal mechanisms, test theories and design better policies – essential charges for nearly all of us at some stage in the research process.' Jennie E. Brand, Jennie E. Brand, Professor of Sociology and Professor of Statistics and Data Science, UCLA 'Every scientist wants to know not just if a causal relationship exists, but why. Wodtke and Zhou offer a clear and up-to-date guide to analyzing causal mechanisms, distilling two decades of methodological advances. Essential reading for social scientists and methodologists – this book will inspire many future scientific breakthroughs.' Kosuke Imai, Professor of Government and of Statistics, Harvard University