Skip to content

Epidurals: Are labor epidurals really linked to autism?

March 23, 2026 · 1 h 9 min

Show notes

Epidurals are widely used and widely trusted for pain relief during labor. So when a 2020 study reported that they might be linked to autism, it raised a troubling question: could a routine medical decision have long-term consequences? We follow that claim from headline to evidence—and watch what happens when other scientists take a closer look. We dig into the original study, a wave of replication studies from around the world, and a meta-analysis that tries to make sense of it all. Along the way, we unpack hazard ratios, Cox regression, inverse probability weighting, and sibling analyses—and why even sophisticated statistical adjustment can’t eliminate confounding. Plus: why bigger datasets don’t solve everything, what happens when results shrink after adjustment, and how a controversial study turned into a case study in science working as it should. Bonus: our first guest journalist interview!

Statistical topics

  • Confounding
  • Cox regression
  • Hazard ratios
  • Inverse probability weighting (IPTW)
  • Multivariable adjustment
  • Observational studies
  • Residual confounding
  • Retrospective cohort studies
  • Sibling analysis
  • Statistical adjustment
  • Statistical significance vs practical significance
  • Survival analysis

Methodological morals

  • “Every time you adjust the model and the effect gets smaller, that's the universe whispering, maybe don't build a causal story out of this.”
  • “Consistency across studies is gold.”
  • “There's more to the story than the statistics.”



References



Kristin and Regina’s online courses:

Demystifying Data: A Modern Approach to Statistical Understanding

Clinical Trials: Design, Strategy, and Analysis

Medical Statistics Certificate Program

Writing in the Sciences

Epidemiology and Clinical Research Graduate Certificate Program

Programs that we teach in:

Epidemiology and Clinical Research Graduate Certificate Program


Find us on:

Kristin - LinkedIn & Twitter/X

Regina - LinkedIn & ReginaNuzzo.com


  • (00:00) - Intro
  • (01:40) - Why autism is hard to study
  • (05:18) - The original 2020 study
  • (11:38) - Results & hazard ratios
  • (15:24) - Confounding & adjustment
  • (26:32) - Criticism & plausibility
  • (34:11) - Replications begin
  • (44:38) - Converging evidence & meta-analysis
  • (50:48) - What does it mean?
  • (53:38) - Guest & wrap-up

All episodes of Normal Curves: Sexy Science, Serious Statistics

Settings

Display

Language

Decides which stations you see first on the home page.

History

Recently played stations and episodes and your latest searches are only stored in this browser.

Notifications

A short notice when a podcast you follow has a new episode. Turn off single podcasts with the bell on their page.

Account

Save favorites – in the app and on the website.

Keyboard shortcuts

/
Open search
Space
Play or pause
← →
In the player: back 15 s, forward 30 s (episodes) · in a row: next tile
↑ ↓
In a row: target within the tile
Home / End
In a row: first or last tile
Esc
Close window or menu
?
This overview
Now playing

Go to station page

Play next

    Add episodes with “Play next” – they play after the current episode.