Nothing is a scientific debate if you set the standard of evidence so high that nothing will satisfy it.
-
Europeans are included in the graph only for illustrative purposes. The regression is of IQ on African ancestry in the black sample.
Better to use the overall regression model as this includes the variance in ancestries from the various other subgroups. One strength is that the ancestry betas are essentially the same no matter which (sub)sample one fits it to.
-
-
If all groups are included in the same simple regression, the coefficients will be mainly determined by the largest group(s).
-
That's fine. White people don't really contribute to the estimation because they are ~100% European and European ancestry is the reference ancestry so it's beta is not directly estimated. Compare results for everybody vs. non-Whites (Table 12 vs. Table 17).
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.