1 UC Davis courses
- EPI 205: Principles of Epidemiology
- EPI 206: Epidemiologic Study Design
- EPI/SPH 207: Advanced Epidemiologic Methodology
- EPI 225: Advanced Topics in Epidemiology Methods
- POL 285: Statistics of Causal Inference in Political Science
- MGB/MGP/MGT 454A: Causal Inference and Statistical Experiments
- PSC 204B: Causal Modeling of Correlational Data
- PSC 205C: Structural Equation Modeling
Course search options:
2 Courses elsewhere
- PH784 Advanced Social Epidemiology: Methods: a half-semester course at Boston University School of Public Health, with lecture slides and problem sets that cover causal inference and its methods
3 Online Videos
- Introduction to Causal Inference
- Online Causal Inference Seminar series
- UC Davis CTSC presentation library, by Clinical and Translational Science Center: recordings and slides of CTSC talks, including Introduction to Causal Inference above
4 UC Davis Datalab learning group
Other links:
- Introduction to Causal Methods, by A. Colin Cameron: slides with brief examples of randomized trials, instrumental variables, directed acyclic graphs, panel data, difference in differences and regression discontinuity, most with Stata code and data
- https://datalab-icmat.github.io/causal_reading_group.html
-
Lab exercises by Ben Noble
- author’s site: https://benjaminnoble.org/
5 Books
Free online books:
-
Causal Inference: The Mixtape, by Scott Cunningham: a free online textbook, with its data files and code in a public repository
- data and code: https://github.com/scunning1975/mixtape
- Causal Inference in R, by Malcolm Barrett, Lucy D’Agostino McGowan and Travis Gerke: a free online book in the tidyverse style, loosely structured around Hernán and Robins’s What If
- Statistical Tools for Causal Inference, by Sylvain Chabé-Ferret: an open source collaborative book that starts from the Rubin causal model
- Causal Inference for The Brave and True, by Matheus Facure: a light-hearted but rigorous introduction to impact estimation and sensitivity analysis, in Python
- Applied Causal Inference, by Uday Kamath, Kenneth Graham and Mitchell Naylor: from a practical overview of causal inference to applications of causality in machine learning
- Applied Causal Analysis (with R), by Paul C. Bauer: the script for a seminar at the University of Mannheim
- Which causal inference book you should read, by Brady Neal: a flowchart for choosing a causal inference book
Code for Hernán and Robins’s What If:
- R and Stata code for the exercises in What If: with R code by Joy Shi and Sean McGrath and Stata code by Eleanor Murray and Roger Logan
- R notebook for part 2 of What If, by Malcolm Barrett
- R programs for chapters 12 and 13 of What If
6 Software
- TrialEmulation, by Isaac Gravestock, Li Su, Roonak Rezvani, Julia Moesch and Juliette Limozin: an R package that emulates a target trial in observational time-to-event data, estimating intention-to-treat and per-protocol effects with marginal structural models
7 Papers
- Hernán (2018): argues that observational studies should name their causal goal instead of describing causal effect estimates as associations
- Ibeling and Icard (2021): proves that causal inference without substantial assumptions is possible only for a meager set of structural causal models, so the assumptions that license causal conclusions cannot be verified from data