Penalization for small n problems: case study of Steam games
For many kinds of ranking websites, users are naturally going to be interested in the leaderboard or top list, the best of the best. This is the same thing for…
Two new review articles on national IQs
Heiner Rindermann sent me his new review paper: Rindermann, H. (2025). Low cognitive ability estimates in developing countries: A statistical analysis of their credibility. Human Evolution, 40(3–4), 257–284. https://doi.org/10.14673/HE2025341159, Developing countries…
Migrant selection and informative priors
Chris Rufo wasn't happy with the recent American experience with the Somalians scamming the welfare state and wrote about how one should take into account "which national populations" people wish…
Classification error and relative rates
Our latest big project on mugshots and race misclassification by the US law enforcement. It is currently going viral on X: You can start by reading the thread summary, or…
Are IQ scales interval or ordinal?
One of the more obscure objections to intelligence testing is that really the tests are only on ordinal scale, and thus many of the usual statistical operations are undefined. Recall,…
How does one correct for measurement error in sibling models?
There was a lot of discussion regarding the corrections for measurement error used in the recent Herasight intelligence polygenic score paper. I covered it for Aporia. I want to dive…
How to norm a score
Suppose you have created a new scale of something ("Science Blog Rating Scale"). It can be psychology or some other soft science, but it doesn't have to be. Suppose you…
On having negative knowledge
I'm reading Jason Brennan's 2016 book Against Democracy, actually in favor of votes weighted by competence, which he calls epistocracy. In discussing the very low levels of political knowledge seen…
What makes a good computer game? An analysis of Steam ratings
What makes a better computer game? While we can discuss game design (e.g. I studied skill vs. randomness before), we can also take an empirical approach. What we need is…
Bayesian hereditarianism
In august 2023, Sean Last wrote an important post that didn't receive enough attention. His point was that model comparisons are not correctly (Bayesically) applied in the hereditarianism vs. egalitarianism…
- 1
- 2
- 3
- 4
- …
- 8
- Go to the next page