Density estimation on the spaces of symmetric and rectangular matrices (Q1369299)

This paper is concerned with estimating unknown density functions of distributions on the space S(m,n) of all m\(\times\)n symmetric matrices and on the space R(m,p) of all m\(\times\)p rectangular matrices. The author has considered two methods, kernel density estimation and density estimation by orthogonal series, and illustrates them with examples for normal kernel density functions and for Hermite orthonormal bases with symmetric and rectangular matrix arguments on S(m,n) and R(m,p), respectively. The problem of estimating unknown joint density functions of multiple random matrices is also discussed.