Week 3: Causal Inference Methods

🎯 Learning Objectives

By the end of this session, you should be able to:

  • Select covariates based on the principles of confounder selection
  • Critically yet constructively interpret causal social epidemiology studies that are likely affected by unmeasured confounders and selection bias
  • Interpret findings from fixed effects and quasi-random approaches while acknowledging their key assumptions as well as pros and cons
  • Explain why there is no “hierarchy” in these different approaches

📅 Date and Time

Monday, September 22, 2025 | 10:00 AM–12:50 PM
Location: Boston University School of Public Health (CTC 460)

🗣️ Lecture Overview

We will learn alternative approaches to causal identification commonly used in social epidemiology: between-comparison based on covariate adjustment, within-comparison using fixed regression, and quasi-random methods.

📚 Required Readings

  • VanderWeele TJ. Principles of confounder selection. European journal of epidemiology. 2019 Mar 15;34:211-9.
  • Krieger N, Davey Smith G. The tale wagged by the DAG: broadening the scope of causal inference and explanation for epidemiology. International journal of epidemiology. 2016 Dec 1;45(6):1787-808.

📖 Optional Readings

  • Commentaries for Krieger & Davey Smith (2016)
    • e.g., VanderWeele TJ. Commentary: on causes, causal inference, and potential outcomes. International journal of epidemiology. 2016 Dec 1;45(6):1809-16.
  • Imbens GW. Potential outcome and directed acyclic graph approaches to causality: Relevance for empirical practice in economics. Journal of Economic Literature. 2020 Dec 1;58(4):1129-79.
    • Critiques of DAGs by an econometrician. Do you buy their arguments?
  • Hernán MA, Hernández-Díaz S, Robins JM. A structural approach to selection bias. Epidemiology. 2004 Sep 1;15(5):615-25.
  • VanderWeele TJ, Ding P. Sensitivity analysis in observational research: introducing the E-value. Annals of internal medicine. 2017 Aug 15;167(4):268-74.
  • Hernán MA, Robins JM. Instruments for causal inference: an epidemiologist’s dream?. Epidemiology. 2006 Jul 1;17(4):360-72.
  • Shiba K, Kawahara T. Using propensity scores for causal inference: pitfalls and tips. Journal of epidemiology. 2021 Aug 5;31(8):457-63.
    • On similarities and differences between various propensity score methods in terms of causal assumptions, modeling assumptions, and causal estimand under consideration.

🎬 Lecture Slides

Use your keyboard arrows to navigate the slides below. You can also view them in fullscreen.

📥 Download Slides

Download the lecture slides in your preferred format:

📄 Download HTML 📄 Download PDF

Note: For PDF, the link will open the print view. Use your browser’s print function (Ctrl+P / Cmd+P) and select “Save as PDF”.

📚 After the Lecture

💻 Problem Set 3

Your main assignment for this week.

➡️ Go to Problem Set 3

📓 Syllabus

➡️ Review the Course Plan


Last updated: September 22, 2025