A recent article by Samorodnitsky and co-authored by two renowned censorship champions, namely, Kevin Bird and Rebecca Sear, requests that all published papers that have ever used Lynn & Vanhanen (2006) national IQs (or subsequent, revised version, up to Becker & Lynn,
seeing the name Samorodnitsky almost gave me a heart attack, I had thought the guy who developed the theory of heavy tailed distributions was now railing against IQ
Becker & Lynn (2019, p. 37) did this. They averaged the school assessment and NIQ, as alternative measure for their NIQ. I see some strength and weakness. On the positive side, assuming no systematic bias for either NIQ and assessment, averaging cancels out measurement errors. On the negative side, it could be that national assessment measures something more than just intelligence, although the evidence suggests this is likely not the case, it's not definitive evidence and I could see why people ask for more thorough investigation. Furthermore, little is known about measurement invariance of either NIQ and school assessment for very low IQ countries, such as African countries. In fact, it could be that NIQ differences reflect intelligence to a lesser degree than school assessment, if nuisance ability such as differences in motivation accounts for a larger share of the group difference in NIQ. Again, there is no study thus far on item bias across countries contrasting high to medium/low IQ levels. But if I had to criticize NIQ, this the point I would make. Given the current state of research and uncertainty surrounding NIQ, I would use all alternatives I could.
For some anomalous countries such as Ireland, it sure seems to improve interpretability, because we all knew this low IQ for Ireland is just unbelievable, so average could only improve the resulting outcome. But perhaps for less known countries with some disparate NIQ/assessment, such an average would make less sense.
seeing the name Samorodnitsky almost gave me a heart attack, I had thought the guy who developed the theory of heavy tailed distributions was now railing against IQ
What do you make of Seb Jensen’s attempt at estimating changes in IQ using the national IQs score + scholastic tests like PISA. https://open.substack.com/pub/sebjenseb/p/changes-in-relative-cognitive-performance?r=1sg94k&utm_medium=ios
If you look at a country like Ireland, the national IQ scores are low. However, their scholastic results are very good. Seb puts them at about 100.
Becker & Lynn (2019, p. 37) did this. They averaged the school assessment and NIQ, as alternative measure for their NIQ. I see some strength and weakness. On the positive side, assuming no systematic bias for either NIQ and assessment, averaging cancels out measurement errors. On the negative side, it could be that national assessment measures something more than just intelligence, although the evidence suggests this is likely not the case, it's not definitive evidence and I could see why people ask for more thorough investigation. Furthermore, little is known about measurement invariance of either NIQ and school assessment for very low IQ countries, such as African countries. In fact, it could be that NIQ differences reflect intelligence to a lesser degree than school assessment, if nuisance ability such as differences in motivation accounts for a larger share of the group difference in NIQ. Again, there is no study thus far on item bias across countries contrasting high to medium/low IQ levels. But if I had to criticize NIQ, this the point I would make. Given the current state of research and uncertainty surrounding NIQ, I would use all alternatives I could.
For some anomalous countries such as Ireland, it sure seems to improve interpretability, because we all knew this low IQ for Ireland is just unbelievable, so average could only improve the resulting outcome. But perhaps for less known countries with some disparate NIQ/assessment, such an average would make less sense.