@lakens - I'm not a fan of Bayes factors. Hard to believe they would be misused more than p-values though.https://twitter.com/lakens/status/857324480812773382 …
-
In what situation? If a) you keep sampling on, or b) if you keep throwing away the data and start over again?
-
-
Aha I thought you meant (a). But even with (b), I bet you'll have to try a lot more often than with p-values.
-
Sure, but that's just because p =.05
BF = 3. BF 10 p = .005. Bayesian stats isn't QRP proof. Values fromhttps://replicationindex.wordpress.com/2015/04/30/replacing-p-values-with-bayes-factors-a-miracle-cure-for-the-replicability-crisis-in-psychological-science/ … -
And you'll say: but at least it helps for the issue of optional stopping. Sure. But conducting such small studies to begin with is dodgy.
-
Agreed. More important is that if you sample enough data, BF will always converge to either strong rel evidence for H0 or H1, as it should.
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.