@KirkegaardEmil @JelteWicherts In the 3-cat. var., 90% of data is in the middle, making the variance even smaller than the 2-cat variable.
Correcting for n-level discretization? http://emilkirkegaard.dk/en/?p=5834 Perhaps @AboveMeOnlySky @JelteWicherts knows?pic.twitter.com/njhwU4avEM
-
-
-
@AboveMeOnlySky
@JelteWicherts Studies often use equal-ranged bins tho. E.g. European ancestry split into quartiles.pic.twitter.com/QAuGcTQAuB
-
@AboveMeOnlySky
@JelteWicherts But you are right, 86% of datapoints go into the central cat using default binning.
End of conversation
New conversation -
-
-
@KirkegaardEmil@JelteWicherts Use equal-sized bins and the anomaly disappears.Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
@KirkegaardEmil@JelteWicherts Great visualization!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.