http://infoproc.blogspot.com/2015/04/iq-prediction-from-structural-mri.html
These authors use machine learning techniques to build sparse predictors based on grey/white matter volumes of specific regions. Correlations obtained are ~ 0.7 (see figure).
I predict that genomic estimators of this kind ( http://arxiv.org/abs/1408.3421 ) will be available once ~ 1 million genomes and cognitive scores are available for analysis. See also Myths, Sisyphus and g ( http://infoproc.blogspot.com/2013/04/myths-sisyphus-and-g.html ).
In this paper, we propose a novel framework for IQ estimation using Magnetic Resonance Imaging (MRI) data. In particular, we devise a new feature selection method based on an extended dirty model for jointly considering both element-wise sparsity and group-wise sparsity...
We perform two experiments to test the performance of our method by using the MRI data collected from 164 typically developing children between 6 and 15 years old. In the first experiment, we use a multi-kernel Support Vector Regression (SVR) for estimating IQ values, and obtain an average correlation coefficient of 0.718 and also an average root mean square error of 8.695 between the true IQs and the estimated ones. In the second experiment, we use a single-kernel SVR for IQ estimation, and achieve an average correlation coefficient of 0.684 and an average root mean square error of 9.166. All these results show the effectiveness of using imaging data for IQ prediction, which is rarely done in the field according to our knowledge.
Whoa. Did not see this one coming, but I really ought to have. I have not delved as deeply in cognitive neuroscience as I once did and getting taken by surprise on this one is the result.
Of interest to the statistics method-minded are how they used their sample data. Pretty sweet use of a relatively small data set.
Hsu writes that this will point to genomic predictors once the data set is large enough. I am not so sanguine, given that we are coming to a better understanding of how the "trash" or "filler" DNA bits have an effect on the organism. That is an awful lot of factors and a mere one million element sample set will be strained to generate such a predictor. We will see. Sooner than we expected.
