My challenge to folks who are skeptical about IQ tests such as the Stanford-Binet or WAIS-R: Develop your own measure of general cognitive ability and show that it has higher reliability & validity in predicting real-world success. I'll wait.
-
This Tweet is unavailable.
-
This Tweet is unavailable.
Given a decent number of mental tests (about a dozen) and a decent sample of test-takers (at least a few hundred), the g factor extraction is highly robust across different factor analysis methods. Anyone who's worked with test data knows this.
-
-
But one of Taleb's points is that the common variance extracted from these different sources is all from the left tail of the distribution - therefore it is more accurate to call it "idiot quotient." No predictive validity or discriminatory power in the high IQ regime.
-
Does it need to achieve that? Do we actually have a reason to care about the difference between an IQ of 150 and 155 except for bragging rights? Or is approximate placement on the curve still useful?
- 2 more replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.