Revolution in science: after 150 years, the American Statistical Association finally says don't use p-values:http://www.r-bloggers.com/after-150-years-the-asa-says-no-to-p-values/ …
-
@pmddomingos@rsalakhu That's not what they are saying. It would certainly be an error to stop using p-values.
@tdietterich @rsalakhu That's what it amounts to. And p-values are the main reason "most published research findings are false" (Ioannidis).
-
-
@pmddomingos@rsalakhu Adaptive statistics promises to account for multiple testing and other design decisions. Safe p-values avoid errors! -
@tdietterich@rsalakhu Personally, I think that (for example) controlling the false discovery rate is a better idea. - Näytä vastaukset
Uusi keskustelu -
-
-
@pmddomingos@rsalakhu The problem isn't p-values, it is how people do the data analysis. See http://errorstatistics.com/2016/03/07/dont-throw-out-the-error-control-baby-with-the-bad-statistics-bathwater/ …Kiitos. Käytämme tätä aikajanasi parantamiseen. KumoaKumoa
-
Lataaminen näyttää kestävän hetken.
Twitter saattaa olla ruuhkautunut tai ongelma on muuten hetkellinen. Yritä uudelleen tai käy Twitterin tilasivulla saadaksesi lisätietoja.