Robust Distance Covariance

Abstract

Distance covariance is a popular measure of dependence between random variables. It has some robustness properties, but not all. We prove that the influence function of the usual distance covariance is bounded, but that its breakdown value is zero. Moreover, it has an unbounded sensitivity function, converging to the bounded influence function for increasing sample size. To address this sensitivity to outliers we construct a more robust version of distance correlation, which is based on a new data transformation. Simulations indicate that the resulting method is quite robust, and has good power in the presence of outliers. We illustrate the method on genetic data. Comparing the classical distance correlation with its more robust version provides additional insight.

To appear in International Statistical Review as a discussion paper

References in corpus (14)

• Measuring and testing dependence by correlation of distances
• Detecting causal associations in large nonlinear time series datasets
• Brownian distance covariance
• Equivalence of distance-based and RKHS-based statistics in hypothesis testing
• AM-GCN: Adaptive Multi-channel Graph Convolutional Networks
• Similarity of Neural Network Representations Revisited
• Kernel-based Conditional Independence Test and Application in Causal Discovery
• Learning Domain-Invariant Subspace using Domain Features and Independence Maximization
• DisCo Fever: Robust Networks Through Distance Correlation
• A fast algorithm for computing distance correlation
• Fast robust correlation for high-dimensional data
• Distance Correlation Methods for Discovering Associations in Large Astrophysical Databases
• Interaction pursuit in high-dimensional multi-response regression via distance correlation
• Distance Covariance, Independence, and Pairwise Differences