From my decades-old poster presentation for "Cognitive skill and technology diffusion: An empirical test."
Classic horse race: which better predicted national productivity growth, national average IQ or national average education levels?
The answer is obvious now.
My paper grabbed the data and methods from Benhabib and Spiegel's now-classic Handbook of Economic Growth piece and threw Lynn and Vanhanen's National Average IQ scores into the mix.
Imitate, don't innovate, was my motto here.
Just add one new thing, IQ scores.
Back then, national average IQ scores offered the biggest dataset for cross country skill comparisons.
Now we have the World Bank's Harmonized Learning Outcomes for many countries, which of course continue to find that test scores beat years of education in global horse races.
• • •
Missing some Tweet in this thread? You can try to
force a refresh
"What about the Italians?" is a mic-drop line in most debates over immigrant assimilation.
But to a social scientist, there are no mic-drop lines, just chances to have Claude Code ask the General Social Survey about Scandinavian-American and Italian-American criminality:🧵
These are self-reports of whether a person has ever been arrested, convicted, or either in jail or prison. Ancestry is self-reported as well.
Arrest question asked many times.
"Scandinavians" includes Norwegians, Swedes, and Danes. [Finns are Nordic but not Scandinavian.]
In the early 20C literature-- as with the 2010-era debate over Mexican-American crime-- age was alleged to be the only difference between Scandinavians and Italians, hiding their true equality, and artificially boosting Italian criminality.
And countries that got more immigrants from places with high Tech History scores over the last 5 centuries have better institutions today:
"The significance of these migration-adjusted estimates also suggests that the diffusion of knowledge or innovation through cross-border migration has been crucial for institutional development."
The paper does not show foreigners commit crimes at the same rate as Germans
Instead, it claims to explain why foreigners commit crimes at higher rates than Germans.
So the title is the opposite of the truth.
Academics, please point out this error candidly, openly.
I hope @tylercowen & @ATabarrok will note the misinterpretation of multivariate regression in this paper.
And @mattyglesias could help the cause of improved empirical debates by pointing the difference between claiming something is false versus explaining why it's true.
This Reuters post about the study gets at part of the issue, what economists call overcontrol bias, what I've called an Everest Regression:
"Controlling for barometric pressue, Everest is the same altitude as Death Valley."