I'd forgotten about this. It's still a good idea. Any takers?https://twitter.com/KirkegaardEmil/status/838739870352871425 …
-
so original coefficients would tell how many SDs one percent point change in ancestry X predicts g to change.
-
-
They're comparable if you have constant units. If the sample IQ variation's at least roughly like the pop variation
-
then unstd weight shows how much IQ changes per 1% change in each ancestry which is a lot more meaningful that betas
-
not enough power to do this well, but still interesting imopic.twitter.com/nx8uReyIwS
-
What's the slope then?
-
-
Thanks. Do I get this right: 1% more Euro ancestry increases black IQ by .013 SDs. A hypothetical black w/ 100% Euro
-
ancestry would score 1.3-.83=.47. Actual whites average .2 vs. -.55 for blacks. Taking these at face value would
-
suggest that maybe two-thirds of the gap genetic in the sample.
- 14 more replies
New conversation -
-
-
btw do you have a snippet to install your 'kirkgaard' package? looking at your OSF project and fails b/c depend.
-
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.