@KirkegaardEmil from what file/table did you get the education data from? http://emilkirkegaard.dk/en/?p=5034 I didn't find it in either of the 3 sup
-
@KirkegaardEmil not enough power, but highly suggestive.... :-)pic.twitter.com/qPe78tsC6O
@RCAFDM Suggestive and nothing else. That's why we didn't pursue it more.
-
-
@KirkegaardEmil weak evidence is still evidence imo. If nothing else, the fact that sign/slope in expected direction/magnitude is worth +Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
@KirkegaardEmil knowing. Certainly not decisive though :PThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
@KirkegaardEmil also statistically significant in OLS, including with n-order polynomial income specificationspic.twitter.com/Rn3hBfv7ml
-
@RCAFDM p values are meh. Easy to get those when you do it like that. Not convincing because it is mixed with SIRE effects. -
@RCAFDM The only convincing data is the within SIRE group correlation, but N too small. Also, you need to make g factor from cog vars first. -
@KirkegaardEmil does ping have SIRE data? -
@RCAFDM No, but you can mimic African Americans by selecting persons as you did before (euro+african >= 95%). Maybe real dataset has.
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.