Abstract
In this article, we provide an algorithm for generating valid 4 × 4 correlation matrices by creating bounds for the remaining three correlations that insure positive semidefiniteness once correlations between one variable and the other three are supplied. This is achieved by attending to the constraints placed on the leading principal minor determinants. Prior work in this area is restricted to 3 × 3 matrices or provides a means to investigate whether a 4 × 4 matrix is valid but does not offer a method of construction. We do offer such a method and supply a computer program to deliver a 4 × 4 positive semidefinite correlation matrix.
| Original language | English |
|---|---|
| Pages (from-to) | 53-59 |
| Number of pages | 7 |
| Journal | Applied Mathematics E - Notes |
| Volume | 7 |
| State | Published - 2007 |
Scopus Subject Areas
- Applied Mathematics