How bad are Richard Lynn's 2002 national IQ estimates?
They correlate at r = 0.93 with our current best estimates.
It turns out that they're really not bad, and they don't provide evidence of systematic bias on his part🧵
In this data, Lynn overestimated national IQs relative to the current best estimates by an average of 0.97 points.
The biggest overestimation took place in Latin America, where IQs were overestimated by an average of 4.2 points. Sub-Saharan Africa was underestimated by 1.89 pts.
Bias?
If you look at the plot again, you'll see that I used Lynn's infamously geographically imputed estimates.
That's true! I wanted completeness. What do the non-imputed estimates look like? Similar, but Africa does worse. Lynn's imputation helped Sub-Saharan Africa!
If Lynn was biased, then his bias had minimal effect, and his much-disdained imputation resulted in underperforming Sub-Saharan Africa doing a bit better. Asia also got a boost from imputation.
The evidence that Lynn was systematically biased in favor of Europeans? Not here.
Fast forward to 2012 and Lynn had new estimates that are vastly more consistent with modern ones. In fact, they correlate at 0.96 with 2024's best estimates.
With geographic imputation, the 2012 data minimally underestimates Sub-Saharan Africa and once again, whatever bias there is, is larger with respect to Latin America, overestimating it.
But across all regions, there's just very little average misestimation.
Undo the imputation and, once again... we see that Lynn's preferred methods improved the standing of Sub-Saharan Africans.
There's really just nothing here. Aggregately, Lynn overestimated national IQs by 0.41 points without imputation and 0.51 with. Not much to worry about.
The plain fact is that whatever bias Lynn might have had didn't impact his results much. Rank orders and exact estimates are highly stable across sources and time.
It also might need to be noted: these numbers can theoretically change over time, even if they don't tend to, so this potential evidence for meager bias on Lynn's part in sample selection and against in methods might be due to changes over time in population IQs or data quality.
It might be worth looking into that more, but the possibility of bias is incredibly meager and limited either way, so putting in that effort couldn't reveal much of anything regardless of the direction of any possible revealed bias in the estimates (not to imply bias in estimates means personal biases were responsible, to be clear).
Some people messaged me to say they had issues with interpreting the charts because of problems distinguishing shaded-over colors.
If that sounds like you, don't worry, because here are versions with different layering:
• • •
Missing some Tweet in this thread? You can try to
force a refresh
After the Counter-Reformation began, Protestant Germany started producing more elites than Catholic Germany.
Protestant cities also attracted more of these elite individuals, but primarily to the places with the most progressive governments🧵
Q: What am I talking about?
A: Kirchenordnung, or Church Orders, otherwise known as Protestant Church Ordinances, a sort of governmental compact that started cropping up after the Reformation, in Protestant cities.
Q: Why these things?
A: Protestants wanted to establish political institutions in their domains that replaced those previously provided by the Catholics, or which otherwise departed from how things were done.
What predicts a successful educational intervention?
Unfortunately, the answer is not 'methodological propriety'; in fact, it's the opposite🧵
First up: home-made measures, a lack of randomization, and a study being published instead of unpublished predict larger effects.
It is *far* easier to cook the books with an in-house measure, and it's far harder for other researchers to evaluate what's going on because they definitionally cannot be familiar with it.
Additionally, smaller studies tend to have larger effects—a hallmark of publication bias!
Education, like many fields, clearly has a bias towards significant results.
Notice the extreme excess of results with p-values that are 'just significant'.
The pattern we see above should make you suspect if you realize this is happening.
Across five different large samples, the same pattern emerged:
Trans people tended to have multiple times higher rates of autism.
In addition to higher autism rates, when looking at non-autistic trans versus non-trans people, the trans people were consistently shifted towards showing more autistic traits.
In two of the available datasets, the autism result replicated across other psychiatric traits.
That is, trans people were also at an elevated risk of ADHD, bipolar disorder, depression, OCD, and schizophrenia, before and after making various adjustments.
Across 68,000 meta-analyses including over 700,000 effect size estimates, correcting for publication bias tended to:
- Markedly reduce effect sizes
- Markedly reduce the probability that there is an effect at all
Economics hardest hit:
Even this is perhaps too generous.
Recall that correcting for publication bias often produces effects that are still larger than the effects attained in subsequent large-scale replication studies.
A great example of this comes from priming studies.
Remember money priming, where simply seeing or handling money made people more selfish and better at business?
Those studies were stricken by publication bias, but preregistered studies totally failed to find a thing.
It argues that one of the reasons there was an East Asian growth miracle but not a South Asian one is human capital.
For centuries, South Asia has lagged on average human capital, whereas East Asia has done very well in all our records.
It's unsurprising when these things continue today.
We already know based on three separate instrumental variables strategies using quite old datapoints that human capital is causal for growth. That includes these numeracy measures from the distant past.
Where foreign visitors centuries ago thought China was remarkably equal and literate (both true!), they noticed that India had an elite upper crust accompanied by intense squalor.