The persuasive alternative I've heard is that of course there are variations: any two arbitrary subsets of a population are going to have different means and medians for some measure or another. 5% of them will even exceed the 95% confidence interval. But that's not causative.
-
-
-
Alternatively, the baby to bathwater ratio is pretty low. Ignoring small population effects in the face of large personal variation and huge confounding factors in vivo seems wise with a signal this noisy. Would you ever trust that you'd measured a group tendency correctly?
- 5 more replies
New conversation -
-
-
What are you tripping out about now?
-
why should i tell you
- 4 more replies
New conversation -
-
-
i finally figured out why i can never understand what you write!! it's either the clause word length or # of subjects. i have trouble holding that many abstract concepts in memory. but if you ever need to conceal smth from someone with ADD, you've developed a marvelous cipher!
-
look is it my fault that my sentences are best processed by a lisp interpreter
- 2 more replies
New conversation -
-
-
The way that we avoid treating the group tendencies as if they were absolute is to pretend that they don't exist. That's still *not enough* to compensate for bias. I'm not sure what nuanced method you have in mind?
-
i'd probably start with not lying
- 5 more replies
New conversation -
-
-
p sure Stephen Jay Gould
-
reports are varying but fuck that guy too for good measure https://twitter.com/samsaragon/status/1106382562404950016 …
This Tweet is unavailable.
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.