%0 Journal Article %1 reshef_detecting_2011 %A Reshef, David N %A Reshef, Yakir A %A Finucane, Hilary K %A Grossman, Sharon R %A McVean, Gilean %A Turnbaugh, Peter J %A Lander, Eric S %A Mitzenmacher, Michael %A Sabeti, Pardis C %D 2011 %J Science %K Big algorithms, cited, correlation, data data, highly information mining, %N 6062 %P 1518--1524 %R 10.1126/science.1205438 %T Detecting novel associations in large data sets %U http://www.sciencemag.org/content/334/6062/1518 %V 334 %X Identifying interesting relationships between pairs of variables in large data sets is increasingly important. Here, we present a measure of dependence for two-variable relationships: the maximal information coefficient (MIC). MIC captures a wide range of associations both functional and not, and for functional relationships provides a score that roughly equals the coefficient of determination (R2) of the data relative to the regression function. MIC belongs to a larger class of maximal information-based nonparametric exploration (MINE) statistics for identifying and classifying relationships. We apply MIC and MINE to data sets in global health, gene expression, major-league baseball, and the human gut microbiota and identify known and novel relationships.

@article{reshef_detecting_2011, abstract = {Identifying interesting relationships between pairs of variables in large data sets is increasingly important. Here, we present a measure of dependence for two-variable relationships: the maximal information coefficient (MIC). MIC captures a wide range of associations both functional and not, and for functional relationships provides a score that roughly equals the coefficient of determination (R2) of the data relative to the regression function. MIC belongs to a larger class of maximal information-based nonparametric exploration (MINE) statistics for identifying and classifying relationships. We apply MIC and MINE to data sets in global health, gene expression, major-league baseball, and the human gut microbiota and identify known and novel relationships.}, added-at = {2017-01-09T13:57:26.000+0100}, author = {Reshef, David N and Reshef, Yakir A and Finucane, Hilary K and Grossman, Sharon R and McVean, Gilean and Turnbaugh, Peter J and Lander, Eric S and Mitzenmacher, Michael and Sabeti, Pardis C}, biburl = {https://www.bibsonomy.org/bibtex/218303a66d4498017bd26aeb4c5c3c51e/yourwelcome}, doi = {10.1126/science.1205438}, interhash = {bda723a0d064dc5131a81a246b1b5e74}, intrahash = {18303a66d4498017bd26aeb4c5c3c51e}, issn = {0036-8075, 1095-9203}, journal = {Science}, keywords = {Big algorithms, cited, correlation, data data, highly information mining,}, language = {en}, month = dec, number = 6062, pages = {1518--1524}, timestamp = {2017-01-09T14:01:11.000+0100}, title = {Detecting novel associations in large data sets}, url = {http://www.sciencemag.org/content/334/6062/1518}, urldate = {2012-03-03}, volume = 334, year = 2011 }