Learning Bayesian Statistics cover image

#37 Prophet, Time Series & Causal Inference, with Sean Taylor

Learning Bayesian Statistics

00:00

Is There a Future for Casual Inference?

I think it's inevitable that all of us should be interested in causal inference, because models that don't have some sort of causal interpretation are often a little vacuous. The easiest way to understand causality is to just intervene. Just literally make changes and see what happens. And i'm growing less interested in those debates about whether what you were trying to estimate was eithen knowable or not. So i'm an experimentalist. I really care about how do we design the data sets that we need. In a world where you can't experiment, causal inference is almost too hard to do.

Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner