a common complaint is that iq tests are probably biased because of race differences in the designers and takers
-
-
Show this thread
-
so, why not use a multipass measurement? heres how it works
Show this thread -
each ethnic group sends its best psychometricians together to design a 100/15 scale iq test that gives its ethnicity the largest advantage they can manage over other ethnic groups taking the same test
Show this thread -
then, subjects from each race will take each races test you average out the subjects scores across ethnic group tests, and then look at mean differences for these
Show this thread -
I think this requires assuming that every ethnic groups psychometricians are equally good, if how good psychometricians are is positively correlated with "true" group iq differences will be exaggerated
Show this thread -
anyway i cant guarantee the statistical properties of this instrument but i think my novel approach to handling bias issues in psychometrics is poised to solve a lot of problems and further i desire funding
Show this thread
End of conversation
New conversation -
-
-
a white person thought up the multipass measurement solution sooo...
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
This Tweet is unavailable.
-
Hm yes if n > 2
End of conversation
-
-
-
This Tweet is unavailable.
-
which ethnicity is the original g, send tweet
End of 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.