It's easy, you just include both the interactions and the main effects and see which predicts what. See here for an example of US counties. Racial diversity is associated with worse outcomes, until one adds the main effects and IQ. http://rpubs.com/EmilOWK/racial_homogeneity_study_2017 …
The key to understanding it is that a given area can have high diversity for multiple reasons. An area with a 50-50 White-Asian split has high diversity, but is not expected to perform poorly because composite groups perform well.
-
-
Compare with an area with 50-50-Black-Hispanic mix. This will perform poorly because the constituent groups do so, but it has the exact same amount of diversity as the 50-50 White-Asian one. Statistically, thus, one can work out which predicts what.
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.