>R-squared per se may or may not be indicative of the 'scientific value' of
>the finding.
I agree with all you said. My only point, lifted from Gould, was that their strongest case was able to explain 5% of social outcomes, which is pretty useless. On their own terms it's bullshit. Their own terms are even more bullshit than their stats, but I don't think anyone here would disagree.
Doug