Boris Sobolev (@soboleffspaces) 's Twitter Profile
Boris Sobolev

@soboleffspaces

𝗦𝗰𝗵𝗼𝗹𝗮𝗿/𝗔𝘂𝘁𝗵𝗼𝗿/𝗧𝗲𝗮𝗰𝗵𝗲𝗿 • causality in plain language • linktr.ee/sobor

ID: 1201157750144655365

calendar_today01-12-2019 15:15:16

5,5K Tweet

1,1K Followers

70 Following

Boris Sobolev (@soboleffspaces) 's Twitter Profile Photo

The same concern applies to epidemiology training. In my experience with thesis proposals, there is a growing trend of fitting research questions to a statistical technique.

Boris Sobolev (@soboleffspaces) 's Twitter Profile Photo

And on any other night! "You become responsible, forever, for what you have tamed" from The Little Prince I love my cats, Musya and Benji.

Judea Pearl (@yudapearl) 's Twitter Profile Photo

Exciting breakthrough from Elias Bareinboim -- a counterfactual-calculus (cfl-calculus), akin to do-calculus, for handling identification problems in Layer-3 of the Causal Hierarchy.

Boris Sobolev (@soboleffspaces) 's Twitter Profile Photo

Congratulations to Jacob on a successful defense! What a feast for causal inference: causal diagrams, minimal adjustment sets, mediation analysis, direct and indirect effects, probability of benefit — all in the context of cutting-edge clinical practice! Judea Pearl

Congratulations to <a href="/JacobJHutton/">Jacob</a> on a successful defense!

What a feast for causal inference: causal diagrams, minimal adjustment sets, mediation analysis, direct and indirect effects, probability of benefit — all in the context of cutting-edge clinical practice!

<a href="/yudapearl/">Judea Pearl</a>
Jacob (@jacobjhutton) 's Twitter Profile Photo

Adan Z Becerra, PhD Boris Sobolev Judea Pearl Yes a counterfactual mediation analysis was used to estimate the Natural Direct Effect of recognition in out of hospital cardiac arrest. Example: pubmed.ncbi.nlm.nih.gov/37453691/

Boris Sobolev (@soboleffspaces) 's Twitter Profile Photo

That’s not correct! 👇🏻 The assumption is much milder. We just need to assume that the factors we condition on (or stratify on, in epi lingo) block all chains of dependency that could connect the exposure and the outcome. A minimally sufficient adjustment set may not include