Lazy HBDers And Statistics
Thumb sailer
January 23, 2012, 01:21 PM
Print Friendly and PDF
Chuck at Occidentalist has been blogging up a storm lately of statistical analyses on various interesting questions. He vents:
What really frustrates me is Lazy HBD. There are dozens of public use data sets waiting to be explored from a HBD perspective. Statistical packages can be downloaded for free. All sorts of HBDish questions can be addressed: Do 2nd generation Blacks do worse on cognitive tests than 3rd+ generation Blacks? Do mixed White and Asians outperform Whites? What is the standardized difference between first, second, and third generation Hispanics controlling for SES? Does color correlate with IQ in the Hispanic population? Does color correlate with crime in the Black population? But it seems that few are interested. I don’t get it.

I`d get right on it, but I have to take a nap first. 

Seriously, there truly is a huge amount of data out there. Various longitudinal studies have been going on for decades that follow thousands of individuals throughout their lives. The 1979 National Longitudinal Study of Youth is the most famous because Herrnstein and Murray made it the centerpiece of The Bell Curve. But there are many other ones. 

Of course, it`s a lot of work to do it right, as Chuck`s wrestle through multiple blog posts with the old question of whether light-skinned blacks score higher on IQ tests than do dark-skinned blacks. Richard E. Nisbett argued that the lack of a correlation falsifies the theory that racial gaps in IQ are partly genetic. But the answer Chuck came up with appears to be ultimately yes there is a correlation, although it`s not enormous. But as Chuck`s work showed, there are a fair number of wrinkles that must be dealt with. 

Meanwhile, Inductivist looks at the Add Health questionnaire data to see if respondents overrate their own intelligence versus their scores on the survey`s vocabulary tests:

First, people do have a tendency to rate their intelligence correctly—self-described intelligence is positively correlated with measured IQ—but the tendency is only moderate. Next, males are not more likely than females to inflate their smarts. By contrast, blacks are significantly more likely to—compared to whites. The other racial/ethnics groups do not differ from whites.