Maximal information coefficient

In statistics, the maximal information coefficient (MIC) is a measure of the strength of the linear or non-linear association between two variables X and Y. In the linear case, MIC reduces to r, the Pearson coefficient.[1]

The MIC belongs to the maximal information-based nonparametric exploration (MINE) class of statistics.[2] MIC outperforms competing methods when it comes to "generality" and "equitability"[3]

References

  1. ^ Speed, T. (2011). "A Correlation for the 21st Century". Science 334 (6062): 1502–1503. doi:10.1126/science.1215894. PMID 22174235. 
  2. ^ Reshef, D. N.; Reshef, Y. A.; Finucane, H. K.; Grossman, S. R.; McVean, G.; Turnbaugh, P. J.; Lander, E. S.; Mitzenmacher, M. et al. (2011). "Detecting Novel Associations in Large Data Sets". Science 334 (6062): 1518–1524. doi:10.1126/science.1205438. PMID 22174245. 
  3. ^ http://www.exploredata.net/Overview