You don't think male vs female data has any meaning? How about studies like, (gender based) stereotype threats?
-
-
-
How about not erasing nonbinary identities?
-
Sorry, but gender is still statistically cis male and female. It is such a minority that it's statistically unusable data.
-
So you’re so bad at math that you don’t understand how to handle edge cases?
-
No, I'm saying it's not as simple as "stop". Not all genders are necessary data points, depending on the study.
-
My initial complaint was to stop using them in examples of frameworks.
-
Here, one of the most fundamental ML techniques: https://en.wikipedia.org/wiki/Naive_Bayes_classifier#Gender_classification … This example makes me want to *die*
End of conversation
New conversation -
-
-
@ethanwhite is "sex" ok? ;-) -
sex is clearly an important binary epidemiological variable. ~1% may be NA https://doi.org/bttkh4
-
For very limited specific cases, yes.
-
reading up... what do you think of this?https://twitter.com/silvervvulpes/status/814861885250109440 …
-
None of the relevant things about gender or race are biologically based.
End of conversation
New conversation -
-
-
...unless it is to illustrate by example how imperfectly a binary data type captures supposedly dichotomous data.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.
