News for hackers. Stuff that matters.

A comment on Marshmallow Test Fails to Replicate. Parent comment

Re:Marshmallow Test Fails to Replicate by enavari on Friday August 02, 2024 @04:04PM (#41142133)
True, but I remember reading the replication failure rates were twice as much in the social science than in medicine.
[ Parent | on HN ]
Re:Marshmallow Test Fails to Replicate by matthewdgreen on Friday August 02, 2024 @04:50PM (#41142525)
We constantly see small medical studies (<100 participants) posted here on HN that produce exciting results, which then disappear from view and/or fall apart when replicated with larger cohorts.
[ Parent | on HN ]
Re:Marshmallow Test Fails to Replicate by llamaimperative on Saturday August 03, 2024 @11:00AM (#41146947)
How is this different from science working?
[ Parent | on HN ]
Re:Marshmallow Test Fails to Replicate by kjkjadksj on Saturday August 03, 2024 @01:31PM (#41147926)
When it happens in the hard sciences its science working, when it happens in the soft sciences its a replication crisis.
[ Parent | on HN ]
Re:Marshmallow Test Fails to Replicate by llamaimperative on Saturday August 03, 2024 @04:16PM (#41148949)
Haha that seems to be the case!
[ Parent | on HN ]
Re:Marshmallow Test Fails to Replicate by pessimizer on Saturday August 03, 2024 @12:54PM (#41147698)
If that didn't happen, it would mean that math was broken. That's how statistics is supposed to work.
[ Parent | on HN ]