Multi-Way Correlation Coefficient

With the Multi-way Correlation Coefficient, we can analyze the correlation between multiple variables in a dataset simultaneously. This is particularly useful in high-dimensional datasets where traditional pairwise correlation methods may not capture the relationships effectively.

Definition: Let mcor(C)\text{mcor}(C), the multi-way correlation coefficient, be

mcor(C)=1dσ{eigenvalues(C)},\text{mcor}(C) = \frac{1}{\sqrt{ d }} \sigma \{ \text{eigenvalues}(C) \},

where σ\sigma is the Standard Deviation of a set of values, dd the dimension of the dataset and CC the matrix of computed Pearson Correlation Coefficients. 1


Footnotes

  1. Taylor, A. (2020). Multi-way correlation coefficient analysis.

Command Palette

Search for a command to run...