We'll see about that! If they can implement p = .005 'discovery threshold', it will obviously help because it's much harder to QRP the way to that level without direct fraud.
I do feel schadenfreude. For decades, self-righteous, feel good people in social psychology telling us to believe their stuff. No clothing on that field, re-evaluate every claim.https://twitter.com/hardsci/status/1000120298639802368 …
-
-
This Tweet is unavailable.
-
-
I don't think the threshold is going to help much - tbh, I find the idea counterproductive (as do some others who know more than I do: https://psyarxiv.com/9s3y6 ). You can still QRP large data sets, you'll just have to have better funding to collect so much data.
-
I read that, but not convincing IMO. Psychologists will keep doing their student thing and they can't QRP that into p<.005 given null hypothesis using ordinary QRP methods.
-
What about the other issues outlined there? I think the whole focus on singular p-values is a bigger part of the issue. Encouraging replications more and forcing us to justify our alpha would at least make us think more. Hopefully.
End of conversation
-
-
-
But you would have been there no matter what since you're a natural born pessimist. ;)
End of conversation
New conversation -
-
-
Honestly I always knew it was 90% crap, and I wonder why everyone else fell for it.
-
As the saying goes, it's not what you know, it's what you can prove.
- 2 more replies
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.