Resources
Learning Pathways
Start Here: Methods in Causal Inference Series
A four-part tutorial series published in Evolutionary Human Sciences that provides a systematic introduction to causal inference methods.
Part 1: Causal Diagrams and Confounding
Beginner level. Introduces causal directed acyclic graphs (DAGs), which represent assumptions about causal relationships, and confounding bias.
Part 2: Interaction, Mediation, and Time-Varying Treatments
Intermediate level. Covers effect modification, interaction, mediation, and treatments that change over time.
Part 3: Measurement Error and External Validity
Intermediate level. Examines measurement error and threats to applying findings across populations and cultures.
Part 4: Confounding in Experiments
Advanced level. Examines how confounding can arise in experiments.
For an interactive introduction to causal DAGs, see Introduction to Directed Acyclic Graphs. For a visual guide to common bias structures, see Common Structures of Bias. For propensity score weighting, start with the WeightIt documentation.
Software and Tools
R Packages
\(\tt{margot}\) A framework for causal inference with panel data, supporting doubly robust estimation and sensitivity analyses. Documentation is at go-bayes.github.io/margot, and the source code is at github.com/go-bayes/margot. Install with devtools::install_github("go-bayes/margot").
ggdag Create causal DAGs to represent a study’s causal assumptions. Documentation is at r-causal.github.io/ggdag, and the CRAN page is cran.r-project.org/package=ggdag. Install with install.packages("ggdag").
WeightIt Weighting tools for covariate balance: making exposure groups more comparable on measured characteristics in observational studies. Documentation is at ngreifer.github.io/WeightIt, and the CRAN page is cran.r-project.org/package=WeightIt. Install with install.packages("WeightIt").
boilerplate Tools for generating standardised boilerplate text and documentation for reproducible research. Documentation is at go-bayes.github.io/boilerplate, and the CRAN page is cran.r-project.org/package=boilerplate. Install with install.packages("boilerplate").
Essential Readings
Core Readings Barrett, M. (2023). ggdag: Analyze and Create Elegant Directed Acyclic Graphs.
Suzuki, E. et al. (2020). Causal Diagrams: Pitfalls and Tips. Intermediate level.
Neal, B. (2020). Introduction to Causal Inference, Chapter 3. Beginner level.
On the Importance of Timing in Data Hernan, M.A. and Robins, J.M. (2024). Causal Inference: What If, Chapter 6. Advanced level.
Tutorial VanderWeele, T.J. and Knol, M.J. (2014). A tutorial on interaction.
Foundational Papers VanderWeele, T.J. (2007). Four Types of Effect Modification. Intermediate level.
VanderWeele, T.J. (2009). On the Distinction Between Interaction and Effect Modification. Intermediate level.
Applied Methods Hernan, M.A. and Robins, J.M. (2024). Causal Inference: What If, Chapters 4-5. Intermediate level.
Measurement Theory VanderWeele, T.J. (2022). Constructed Measures and Causal Inference. Advanced level.
Fischer, R. and Karl, J.A. (2019). A Primer to (Cross-Cultural) Multi-Group Invariance Testing. Intermediate level.
Cross-Cultural Methods He, J. and Van de Vijver, F.J.R. (2012). Bias and Equivalence in Cross-Cultural Research. Intermediate level.
Harkness, J.A. (2003). Questionnaire Translation. Beginner level.
Selection Bias Hernan, M.A. et al. (2004). A Structural Approach to Selection Bias. Advanced level.
Hernan, M.A. (2017). Selection Without Colliders. Advanced level.
Measurement Error Hernan, M.A. and Cole, S.R. (2009). Causal Diagrams for Measurement Error. Intermediate level.
Implementation Guides Bulbulia, J.A. (2024). A Practical Guide to Causal Inference. Beginner level.
Hoffman, K.M. et al. (2023). Comparison Groups in Propensity Score Analysis. Intermediate level.
Outcome-Wide Approaches VanderWeele, T.J. et al. (2020). Outcome-Wide Longitudinal Designs. Intermediate level.
Foundational Papers Athey, S. and Wager, S. (2019). Estimating Treatment Effects with Causal Forests: An Application. Intermediate level.
Wager, S. and Athey, S. (2018). Estimation and Inference of Heterogeneous Treatment Effects using Random Forests. Advanced level.
Kunzel, S.R. et al. (2019). Metalearners for Estimating Heterogeneous Treatment Effects using Machine Learning. Intermediate level.
Practical Applications Davis, J. and Heller, S.B. (2017). Using Causal Forests to Predict Treatment Heterogeneity. Beginner level.
Athey, S. and Imbens, G.W. (2016). Recursive Partitioning for Heterogeneous Causal Effects. Intermediate level.
Video Library
How Do We Learn What Works?
Miguel Hernan
Measurement Constructs
Tyler VanderWeele
Effect Modification and Heterogeneity
Stijn Vansteelandt and Betsy Ogburn
Introduction to Causal Forests
Susan Athey and Stefan Wager
Technical Deep Dive: Causal Forests
Stefan Wager
How Traditional Statistical Mediation Analysis Fails
Stijn Vansteelandt
Design
Synthetic Control Methods
Alberto Abadie
Difference-in-Differences
Paul Goldsmith-Pinkham
Instrumental Variables
Brady Neal
Introduction to Causal Inference
Richard McElreath
Causal Inference in Industry
Sean Taylor
Educational Materials
Workshop Materials
The SPARCC Causal Inference Workshop offers a concise, practical entry point. For a full course sequence, see PSYC 434: Conducting Research Across Cultures.
Reference Texts
Core Textbooks
Causal Inference: What If Miguel A. Hernan and James M. Robins Free Book and Resources. A textbook on causal inference methods with code examples.
Explanation in Causal Inference Tyler VanderWeele Link to OUP page. A strong account of causal mediation analysis and interaction. Ask your library about access.
The Effect Nick Huntington-Klein Free Online. A practical guide with clear visualisations.
Additional Resources
Statistical Rethinking by Richard McElreath provides a Bayesian approach to causal inference. Counterfactuals and Causal Inference by Morgan and Winship focuses on social science applications. Targeted Learning by van der Laan and Rose offers a machine learning perspective on causal inference.
Quick Reference
If you are new to causal inference, begin with our four-part tutorial series. If you need causal DAGs, the ggdag tutorials are a good first step. If you are ready to analyse data, install \(\tt{margot}\) and follow the practical guide. For cross-cultural research, start with Part 3 of the series.
Have a resource to suggest or a broken link to report? Please contact us or submit an issue on our GitHub repository.