S5E5: Causal Pies, Pizza Toppings, and Interaction

S5E5: Causal Pies, Pizza Toppings, and Interaction

From SERious EPI by Sue Bevan - Society for Epidemiologic Research

May 15, 2026 · 44 min

About this episode

The episode discusses the concept of interaction in causal inference, featuring a guest expert and covering various related topics.

In this episode of SERious Epidemiology, Hailey and Matt welcome guest host Dr. John Jackson to discuss Chapter 5 of Causal Inference: What If? This chapter focuses on explaining the concept of interaction. Together, they unpack the often-confusing distinction between causal interaction and effect measure modification. Throughout the discussion they go on (helpful) tangents to talk about factorial trials, risk stratification, DAGs, confounding control, and why students are right to find all of this a bit head-spinning. They also debate additive versus multiplicative interaction, sufficient component causes, causal pies, synergism, antagonism, and whether interaction terms can really tell us anything about mechanisms—or whether they mostly tell us where treatment effects may differ. Along the way, there are excellent examples involving surgery, vaccination, infectious disease. Also, in case you ever wondered, every academic has an ever-growing “papers to read” pile.

People in this episode

Hosts: Hailey, Matt

Guest: Dr. John Jackson

Topics covered

  • causal interaction
  • effect measure modification
  • factorial trials
  • risk stratification
  • DAGs
  • confounding control
  • interaction terms

Keywords

  • causal interaction
  • effect measure modification
  • sufficient component causes
  • synergism
  • antagonism
  • factorial trials
  • vaccination
  • infectious disease

Mentioned in this episode

Books & works: Causal Inference: What If?

More episodes of SERious EPI

Explore listener stats, chart rankings, contacts and more on the SERious EPI podcast page.