Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

how do you determine causation from correlation in experiment where you are unable to separate all the factors? you can't.

not agreeing with one side or other - because i frankly don't know enough about it to form an opinion, but using "correlation != causation" is basically a discussion stopper.



My point is their claim assumes causation despite the fact that we may never be able to prove it. I.e. a strong claim with no evidence besides a correlation.


Nobody suggested there was a causation here as that doesn't matter for what was talked about.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: