IIRC, your sample is so small that the results are compatible with a rather wide range of values.
@akarlin88 in PING dataset, using the simple genetic interpretation of the results, we found 100% heritability of the gap in the USA, which one can then infer ~67% for the USA White vs. SSA African gap from. In other words, about 10 IQ in environmental deficits in Africa.pic.twitter.com/GkChNcxtsz
-
-
-
1300 is not that small.
-
How many of those are black? That's the relevant number.
-
Not exactly. What really matters is the extent of African admixture (if that's the param you want), which is also found in other socially defined race groups. But why guess when you can just read the current draft?https://osf.io/knem8/
-
But of course, if you know a way to gain access to the necessary genomic datasets, I'm all ears. I've spent at least 3 years trying to get access to such data. Being guarded well.
-
I'm perfectly aware of that, but the fact is that you can't say that you found "100% heritability of the gap in the USA." Your estimate may not be significantly different from 100% but it's also not significantly different from considerably lower numbers.
-
My claim was about the point estimate (in the simple genetic interpretation), not whether 95% CI also included some lower values. Of course it did. A little hard to convert, but perhaps congruent with 60% BG h^2 as well (based on the CI).pic.twitter.com/PHw7MXQ0vA
-
Trouble is that the African self-rated race is positive, p close to .05. Some kind of self-identification effect, as I have since found repeatedly in other datasets.
End of conversation
New conversation -
-
Show additional replies, including those that may contain offensive content
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.