I can't tell if this paper is work of genius or fundamentally wrong. 
Usually in these cases, the prior is right and the work is broken somewhere. Usually.
https://www.nature.com/articles/s41380-018-0263-6 …pic.twitter.com/rnajAHf6ws
-
I think so, yes.
Yeah, that would be really stupid. I was assuming they were reporting 10 fold cv results or something.
-
-
If true, my guess is that editors and reviewers weren't familiar with ML methods in general, or the need for rigorous validation methods when applying them. Many social scientists think that just using adjusted R2 is enough!
- 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.