> Using a PCA to prove an intrinsic point
A what point?
> You're aware the vectors in a PCA are just linear combinations of the observed features, right?
Yes, I am. Do you have a reason to think that means PCA is bad at representing similarity and kinship because of this?
As for the Slate Star Codex source - that wasn't to prove anything, just to define the "weak man" term. I would have used "straw man", but then you'd dig up some idiot that genuinely believes whatever it is you're debunking as proof that it's not a straw man.