The correlation between IQ and income | Hacker News Reader

The correlation between IQ and income

pumpkinperson.com

19 pointsamelius13 comments

This article is built around an error in statistical inference. The author uses aggregate data to fit a linear model, then erroneously supposes the slope can be applied to data at the individual level.

It can't.

For example, there are very few megarich people, but the aggregate model gives them 1 (of the 7) data points. That's a lot of weight for a very small group.

From the article:

"It’s common knowledge in psychometric circles that reading comprehension tests are statistically equivalent to IQ tests"

I'm not sure why the author throws this out there, then ignores it. English proficiency is tightly correlated with SES in the US, and one of the historical criticisms of IQ testing is that it mostly tests your ability to understand the questions on the test rather than underlying cognitive capability.

As a result, any conclusions about an IQ gap may be attributable to an education gap, which I doubt very many people would deny exists.

So, low IQ people earn less money because they have lower IQ or they have lower IQ because they earn less money? Higher income implies better lifestyle.

Sorry for bad english.

Has the author ever visited LA? I'm surrounded by rich idiots here.

Ther interwebz says I score 127. Where's my McMansion?

> One problem with this study is that 81% of the sample was black (much higher than the 45% among homeless Americans in general) and these tend to score lower on IQ tests, at least in the general population, however a UK sample of homeless obtained virtually identical scores on the WASI, despite being 96% white.

Uhhh....REALLY not sure what to make of this paragraph. If I'm not missing something, seems to be implying that there's a correlation between race and IQ. This is on HN?

This is not a controversial opinion. It is a statistical fact of psychometrics.

I would be interested to see the results for a comparison of black and white individuals with comparable upbringings.

I have a very, very hard time believing this.

Yes, if you compare the cognitive ability of someone in a 3rd world country to that of someone in a first world country, or someone who grew up in poverty to someone who grew up comfortably, I would be unsurprised to see a difference.

I would be intrigued to be linked to any peer-reviewed study that is not colored by those factors.

Here is a good start

https://en.wikipedia.org/wiki/Race_and_intelligence

Did you read your own source?

> Currently, there is no non-circumstantial evidence that these differences in test scores have a genetic component,

---

> Soon, other studies appeared, contesting these conclusions and arguing instead that the Army tests had not adequately controlled for the environmental factors such as socio-economic and educational inequality between African-Americans and Whites.

----

> The majority of anthropologists today consider race to be a sociopolitical phenomenon rather than a biological one,[34] a view supported by considerable genetics research.

I didn't mean to imply that I knew the answer to your question. I meant that the IQ disparity is a statistical fact, but the cause is a hotly debated area of research without clear answers, and the Wikipedia page is a good primer on the various sides of the debate. The point is that in a study like this you may have to adjust for oversampling by race.

Definitely, but the author is still right to point out that black people are overrepresented in the sample. You could argue that there is still a gap between black and white Americans in terms of education, wealth, etc., and IQ is partially influenced by environmental factors such as maternal/paternal education level (http://www.sciencedirect.com/science/article/pii/S0899900707...).

I think he was trying to say it was evidence of an unrepresentative sample, which is an accurate observation. His counterpoint isn't very sensible though - why not just lead with the U.K. study?

Then it gets into this: "It’s common knowledge in psychometric circles that reading comprehension tests are statistically equivalent to IQ tests..." and that's it for justification of projecting welfare recipient IQs. Okay then. Stopped reading there.

Reply on news.ycombinator.com