The Artists of Data Science cover image

The Book of Why | Dana Mackenzie

The Artists of Data Science

00:00

Do You Have the Right to Control for Causation?

If it's a report of an observational study, then all cause and effect language must be replaced. This is like an official position of the american medical association. Bhut, you're not allowed to call it talk about causation in an article about anse na study. And this is even if you've done the controlling for confoundet. If you have identified everything you could possibly imagine us as he confounder, then you have the right,. i say you have the responsibility, to say: "We've controlled for every con onder we can imagine, and there's nothing left. This must be causation"

Play episode from 50:55
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app