You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
No they don’t. This is what people who don’t deeply understand statistics but want to sound smart say all the time. Correlation implies that you can consider causation, but doesn’t prove it. But people use that phrase as if correlation disproves causation. That’s plain stupidhttps://twitter.com/LeviABx/status/1244970629926998016 …
Correlation implies a suspicion of causation. Also ML teaches us that assuming "correlation implies causation" works fairly well in practice if you're looking at sufficiently many potential correlations over a large enough dataset.
ML models are based 100% on correlation, and they do manage to generalize nicely (with significant limitations)
#ML models ok to use correlation when they’re making _predictions_. But the correlation vs causation paradoxes occur when we are trying to assess _intervening_.
A can predict B if:
A => B
B => A or
C => A and C => B
But (change A) => (change B) iff A => B
@yudapearl
For sure the next steps in causal inference are very complicated but correlation does not imply causation is just not anything smart people who understand causation say as first response.
I think your arguments around correlation signaling possible causation are strong, though your arguments around what smart people say are quite subjective.
Absurd to state that correlation implies causation. Wrong, absurd and dangerous.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
