Into the Impossible With Brian Keating cover image

P-hacking, Reproducibility & the Nobel Prize: Guido Imbens (#269)

Into the Impossible With Brian Keating

00:00

The Problem With Causal Effects

In statistics, the study of causal effects was really in the context of randomized experiments. We take a set of individuals or some population, we split them into two groups and give one to another. And because we actually randomize as Fisher kind of stressed, if you actually do the physical randomization, we know that even if these groups are different, the chances that they're very different is controlled. That's why the Food and Drug Administration insists for new treatments that we actually do randomize experiments.

Play episode from 55:55
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