Choiceology with Katy Milkman cover image

An Accidental Experiment: With Guests Steven Levitt, Solomon Ezra & Stephen Spector

Choiceology with Katy Milkman

00:00

Randomized or Accidental? Which Is Better?

If I have a bunch of data and someone gave me a choice, would I rather have that data generated from a true randomized experiment done right? The answer would always be, I'll take the randomized data because the randomized data is the gold standard. So then why did I just say that accidental experiments are sometimes better than randomized experiments? One reason is because you can have accidental experiments in domains where you can't run randomized experiments. But the other thing is that accidental experiments already happened. They're out there. By the time you analyze the data, you know the result.

Transcript
Play full episode

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