He wasn't trying to make any obvious claim, and he didn't give any clue to what he meant to imply The effect was just to instill in students barely capable of running OLS in Stata, much less interpreting it, a sense of deep epistemic Dread I respect that and I hope it stuck
-
-
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Fisher was (in)famously opposed to the conclusion that they were related, for this reason. (Also maybe because he was paid by tobacco companies.)
-
The real lesson is that huge effect sizes matter and tell you that *something* is going on.
- Show replies
New conversation -
-
-
Fisher made the same point, noting that cancers often cause diffuse discomfort long before diagnosis that smoking could plausibly palliate.
-
oh man Huuuuuuuh
- Show replies
New conversation -
-
-
I choose to believe that this validates my bad habit
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
worse, the only plausible causal explanation I'm aware of was afaik never fully investigated bc if true it implies harm-reduction changes to the cig manufacturing process effective enough that the campaign to "eliminate" smoking for public health reasons isn't strictly necessary
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Did he smoke?
-
I don't believe so he was super straightlaced
End of conversation
New conversation -
-
-
Judea Pearl is one of the main developers and advocates of causal inference. He has a chapter on smoking in his excellent popular book. He is convincing.pic.twitter.com/3cVLcValOz
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.