The correlation aggregation paradox. Within each group, cor is positive, but add all data together, cor is negative.pic.twitter.com/C9zde4Sdth
-
@KirkegaardEmil Nice! you might enjoy this, has some similar empirical examples (e.g. IQ and alcohol) http://journal.frontiersin.org/article/10.3389/fpsyg.2013.00513/abstract …
@rogierK Maybe I should make a shiny app for simulating various kinds of Simpson's paradoxes.
-
-
@KirkegaardEmil Great idea - There is something similar already though, http://vudlab.com/simpsons/ -
@rogierK Pretty good. However, I plan to build a large collection of these, so I might as well add another Simpson's paradox. Can't hurt? :) -
@KirkegaardEmil Agreed, and shiny=more transparant and extendable, great work -
@rogierK Well, someone better give me a PHD soon, so I get more money+time to work on stuff like this. :P
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.