Razib Khan's Unsupervised Learning cover image

Stuart Ritchie: bad science, good science and behavior genetics

Razib Khan's Unsupervised Learning

00:00

What's the Goodheart's Rule?

The file drawer effect, where the studies you see published are not representative of the underlying distribution of results. Goodheart's law states that when the measure becomes the criterion, then then it ceases to be a good measure. And what you actually want is high quality science. The problem is, it's a lot easier to measure just numbers of citations and just tat them up in the way the h in x does, and divide the number of papers. So we need to watch out for things like pre-registration on websites or even people who say they're doing open science but don't really mean it.

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