Surely no risk of overfitting there!
Only a complete pseudoscientist would publish a study with n=51! Surely no normal science would do something like this.... ah, well. :) http://time.com/3614487/fmri-autism-diagnosis/ …pic.twitter.com/0cfSHxRLT4
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Even though I am autistic and am bad at sensing sarcasm it is just blowing me away in this tweet.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
do we even know the specific symptoms that signify autism? I don't think there is even a unified genetic base for once. 17 individuals = 97% accuracy lol
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
51! is a pretty big number
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
This Tweet is unavailable.
-
-
Highly intresting, so important that it seems rigged. The size of sample could be proper if there is clear structural difference in pattern background between entities. Amasing discovery.
-
The two examples of small but significant samples in two sophisticated studies. I reviewed latter recently with strong recommendation for Elsevier publication. Accepted.pic.twitter.com/D9hudxkIUz
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.