News for hackers. Stuff that matters.
Re:Superior IQs associated with mental and physical disorder... by otalp on Saturday December 09, 2017 @02:05PM (#15887402)
Interestingly in analysis of both children and grandmasters, IQ was negatively correlated with chess skills amongst elite players in the group.
Re:Superior IQs associated with mental and physical disorder... by Recursing on Saturday December 09, 2017 @02:09PM (#15887437)
Can you provide a source for that?
Re:Superior IQs associated with mental and physical disorder... by thaumasiotes on Saturday December 09, 2017 @03:43PM (#15888012)
There's really no need; that's exactly what you would expect to see in a thresholded population ("elite players").
Re:Superior IQs associated with mental and physical disorder... by lgas on Saturday December 09, 2017 @04:43PM (#15888334)
Maybe I'm just not that bright but I would expect to see a positive correlation between IQ and exceptional chess ability.
Re:Superior IQs associated with mental and physical disorder... by thaumasiotes on Saturday December 09, 2017 @06:45PM (#15888845)
There is a positive correlation between IQ and chess ability. That does not imply that there should be a positive correlation between IQ and chess ability in a group that has been selected for strong performance in chess.
Re:Superior IQs associated with mental and physical disorder... by 0xcde4c3db on Sunday December 10, 2017 @12:44AM (#15890156)
Is this Simpson's Paradox, or something else?
Re:Superior IQs associated with mental and physical disorder... by thaumasiotes on Sunday December 10, 2017 @01:22AM (#15890244)
Something else. https://en.wikipedia.org/wiki/Statistical_conclusion_validit...

> Restriction of range, such as floor and ceiling effects or selection effects, reduce the power of the experiment, and increase the chance of a type II error.[5] This is because correlations are attenuated (weakened) by reduced variability

If you want to try this for yourself, try generating some fake SAT scores: (a,b) pairs where a and b are normally distributed with mean 500 and sd 100, and where a and b correlate at about 0.8.

Then, from your unbiased data set, select all the pairs for which 1600 >= a + b >= 1300, and check the correlation of a with b in the new, smaller data set.

Just examining this as a thought experiment, you can see that someone with an 800 math score might have a verbal score anywhere from 500 to 800. If we lower the math score, our expectation for the verbal score rises -- someone with a 600 math score will have a verbal score between 700 and 800. That is the basis of the negative correlation in the subgroup, but it's purely an artifact of the way we chose to label data points as being in or out of the subgroup.

Re:Superior IQs associated with mental and physical disorder... by thaumasiotes on Sunday December 10, 2017 @04:29AM (#15890658)
Past the edit window: the 600 math score will of course imply a verbal score between 700 and 1000; the data I described has no caps on individual scores.
Re:Superior IQs associated with mental and physical disorder... by jcranmer on Saturday December 09, 2017 @05:31PM (#15888544)
I'm assuming he's referring to regression to the mean.
Re:Superior IQs associated with mental and physical disorder... by thaumasiotes on Sunday December 10, 2017 @04:21AM (#15890647)
Regression to the mean would only be relevant if you sampled something twice.
Re:Superior IQs associated with mental and physical disorder... by gleb on Saturday December 09, 2017 @04:24PM (#15888244)
Please elaborate
Re:Superior IQs associated with mental and physical disorder... by thaumasiotes on Saturday December 09, 2017 @06:42PM (#15888837)
On the assumption that IQ and "chess skills" both contribute to "chess performance", then everyone achieving a threshold of "chess performance", such as being an "elite player", has been selected to have at least a certain sum of "IQ + chess skills".

This means that, given high IQ, it's not necessary to have good chess skills to be in the elite group, whereas given low IQ, it is necessary to have good chess skills to be in the elite group. This will establish a negative correlation between "chess skills" and IQ within the elite group even though they are positively correlated overall.

Similarly, SAT math and verbal scores tend to be negatively correlated within the student population of any particular university, because universities will reject applicants whose total scores are low, despite the fact that the math and verbal scores are very strongly positively correlated in the larger population.

Re:Superior IQs associated with mental and physical disorder... by gleb on Sunday December 10, 2017 @09:14AM (#15891441)
Thank you, this makes a lot of sense
Re:Superior IQs associated with mental and physical disorder... by tzahola on Sunday December 10, 2017 @05:25AM (#15890807)
Imagine a scatterplot of two correlated variables. Overall there’s a clear tendency for samples to be around the diagonal. Now zoom on the top 1% of the plot and surprise, you’ll see no apparent correlation.