Consistency of the Maximal Information Coefficient Estimator
arXiv:2107.03836v11 citations
Originality Synthesis-oriented
AI Analysis
This addresses a theoretical gap in a widely used statistic for measuring dependence in large datasets, though it is incremental as it fixes an existing error.
The authors proved that the Maximal Information Coefficient (MIC) is a consistent estimator of its population counterpart, correcting an error in a previous argument by Reshef et al. (2016).
The Maximal Information Coefficient (MIC) of Reshef et al. (Science, 2011) is a statistic for measuring dependence between variable pairs in large datasets. In this note, we prove that MIC is a consistent estimator of the corresponding population statistic MIC$_*$. This corrects an error in an argument of Reshef et al. (JMLR, 2016), which we describe.