A New Parametrization of Correlation Matrices

We introduce a novel parametrization of the correlation matrix. The reparametrization facilitates modeling of correlation and covariance matrices by an unrestricted vector, where positive definiteness is an innate property. This parametrization can be viewed as a generalization of Fisher's Z-transformation to higher dimensions and has a wide range of potential applications. An algorithm for reconstructing the unique n x n correlation matrix from any vector in Rn(n-1)/2 is provided, and we derive its numerical complexity.

Automated summary

This study presents a novel parametrization method for correlation matrices, allowing modeling of correlations and covariance matrices using an unrestricted vector and has various potential applications. An algorithm is provided for reconstructing a unique n x n correlation matrix from any vector in Rn(n-1)/2, with its numerical complexity derived.