-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Rushton claimed to have found some, mostly questionnaire based, probably small n, from memory
-
Trouble is that lying/false responding on questionnaires is related to IQ, so there's IQ related bias when comparing groups.
-
Yes, I can see that. Pity that humans are so difficult to observe closely.
-
But findings not replicated here: http://onlinelibrary.wiley.com/doi/10.1002/cbm.541/abstract … maybe sampling error, n only 800 and crime is rare.
-
I read the second study as substantiating the value of self report, even for black respondents.
End of conversation
New conversation -
-
-
@slatestarcodex has looked at some of these studies, but IIRC found them wanting on the "self-reported" grounds -
OKCupid dataset can be used but it suffers from selection bias because people on dating sites are not random
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.