Sunday, March 25, 2007

Map of estimated average IQ by state in US

Above is a mapped visualization of estimated average IQ by state, created by taking the regression equations produced by running the numbers in the data table put together by Richard Lynn in Race Differences in Intelligence where he correlates IQ scores with international math and science test scores (pp 173-175) and then adjusting the nominal test score values (by running an IQ of 98 through the regression equation produced by Lynn's numbers) on the international tests to the NAEP math and science tests in the US.

Many Eyes, a web service similar to Swivel that allows for better aesthetic utilization than its predecessor, provides the engine, and a better and more 'interactive' visualization of the IQ data is on its server, found here (click on each state to see its individual IQ estimate).

Parenthetically, competition in this market is going to greatly enhance the ability of data to be presented more fully, and for models to be better built and understood. My thanks to Fat Knowledge, who alerted me to and keeps up on these rapidly developing web resources.

The dichotomous englightened-coasts vs. ignorant-heartland is helpful as a general paradigm for political-geographical distributions, but not for those based on cognitive firepower. More appropriate is a northern-intelligence vs. southern-'vibrancy' split. As we head northward, we reach the mundane foothills of the Dakotas and without realizing it, we're in banal Canada. Contrast that to the vivacity of the American Southwest, and the always-alive Mexican border towns.

It might also be seen as a jobs-Americans-will-do vs. jobs-Americans-won't-do split. Take Texas (#35), Florida (#42), Arizona (#43), Nevada (#44), California (#46), and New Mexico (#47), bastions of the economically essential immigrant peasantry. Compare these to states like North Dakota (#2), Montana (#4), and South Dakota (#5), where Americans still do the jobs that Americans won't do.

Finally, it can be viewed in relationship to race. Alone, the racial composition of a state 'explains' 72% of that state's estimated IQ, with the two correlating at a robust .85. Expenditures per student, teacher salaries, and classroom size combined explain a paltry 15%. Considered independently, they are statistically insignificant and explain virtually nothing.


5 comments:

Fat Knowledge said...

crush,

Good stuff. I think the map allows you to visualize the data in a way that a table can't. Glad to see you gave it a try.

Many Eyes needs a better way to allow a snapshot picture of the visualization to be included in blog posts. I think what you did is about the best you can do, unless you do a print screen of the visualization and then turn that into a .jpg with photoshop (or my favorite little free image editing software Irfanview).

Do you know what percentage of the difference in state IQs is 'explained' by latitude? Not that that really explains much, but after looking at the map it really jumps out at you.

JSBolton said...

Is the first such map published?
If so, congratulations, you are a pioneer on the frontier of the advancement of human biodiversity experience, perhaps.

crush41 said...

FK,

I'll give it a try, probably using state capitals.

John,

Sometimes a picture is worth a thousand words.

JSBolton said...

http://www.childrenofmillennium.org/science.htmthis site has a US state IQ map, but it seems to use rather old data, and I don't know when it was posted.
It also gives dozens of correlates of IQ which could be of interest.

crush41 said...

John,

That's an intriguing map. The first thing that jumps out is the relatively strong performance of the Southwest--that was the US three decades ago. How literally golden the Golden State has become, and not for the better.

Did you see an actual data table though? I'd like to correlate the site's results with my own, but the visual only gives estimates in ranges of 2 or 3. That's too broad to be of much use.