Peculiar study http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0131613 … smarmily misreported by WaPo http://wpo.st/emcR0 . The graph in the WaPo is not actual data.
@othercriteria But--stop me if I'm wrong here--but WaPo's presentation of the graph seems deeply misleading in that it's not actual data.
-
-
@othercriteria It's the graph of a fitted model, yeah? So there's a bait-and-switch--it looks impossibly clean because it is. -
@othercriteria A point cloud (not sure if that's exactly possible in this context?) would be far less impressive. -
@St_Rev Certainly far less impressive... Though it's roughly consistent with the effect being real and the low-ish n.pic.twitter.com/yKPIsRXXj3
-
@othercriteria Jesus, I missed the y-axis cropping. Ugh. -
@othercriteria They might have a good p-value but the predictive value is clearly nil and zip. -
@othercriteria y'know, eyeballing it, it looks like if you partitioned the F data in the middle and fit the left and right sides separately> -
@othercriteria ...the correlation might reverse completely. -
@othercriteria Which has zero validity for anything, it's just interesting that the data's that crappy. - 1 more reply
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.
. Banned in Sweden. SubGenius, Zhuangist, white-hat troll. Defrocked mathematician. Brain problems.