Smoking....pic.twitter.com/0N1nJTVRQ1
-
@KirkegaardEmil didn't you say the data needed to be adjusted for age or something?
@RCAFDM Yes, but I don't have age data. Remember, I asked you to dig it up. ;) You probably need non-linear adjusting.
-
-
@KirkegaardEmil yeah i gave you county level age data though :PThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
@KirkegaardEmil but yeah.... you think adjust against median age or something else? -
@RCAFDM More variables than one and use LOESS. -
@KirkegaardEmil you mean normalize against multiple age distribution points or against multiple S-factor variables (edu, $, etc)? -
@RCAFDM I mean residualize all the S indicators using LOESS with one or more age variables. -
@KirkegaardEmil oh yeah, wrote a function awhile back normalize multiple vars by age using loess for that MRI study -
@RCAFDM Residualize is the word. ;)
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.