* = actually, this sample was not random (large immigrant populations in UK), and not really small at 23 at that. But these kind of results replicate with 35-70 populations in Denmark too.
Show this thread
The double standards. Supposedly using small, non-random samples* "This should be disqualifying for any job in quantitative social sciences" then I guess there would be a lot of open positions seeing that most soc sci is based on ad hoc student samples.https://twitter.com/AlexStevensKent/status/1124707633183842304 …
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I rarely (if ever) see studies in decent journals with samples as small as n=23 that apply multivariate regression and report p values as if they were meaningful. If such studies are published, they shouldn't be.
-
Non-academic non-scientist view: I’d welcome a moratorium on all student-only studies It’s almost always lazy methodology - if only universities were sited in places near other populations worthy of study
-
Same here. But that's a different issue. Here the issue is application of multivariate regression to a very small sample, which also should not be done.
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.