using an argument about predicted group means for a case filtered on something as out on the tails as *leading a cult* is just nonsense
I think it's really fun to play around with potentially (or even probably) bogus ideas on twitter. it should be play though. when it gets argumentative like this, and when you're going into the minutia about which assumptions about a stat model are ok you're not playing anymore.
-
-
And I am indeed am not “playing” anymore — making inferences about tails is certainly valid enough TO PROPOSE A GODDAMN HYPOTHESIS, which is what I did. In fact it would be a valid enough reason to publish this hypothesis — but not to validate it (yet).
-
There are several levels of inquiry: 1) wild speculative 2) informed hypothetical 3) deductive/empirical (validation) My initial tweet was (1). By explaining my reasoning statistically, I reached (2). I never claimed to be at (3).
-
all I'm really trying to say at this point is "dude, chill, this is just a bull session"
End of conversation
New conversation -
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.