Since the data matrix Z are real and the covariance matrix R greater than zero, which mean that all its eigenvalues on matrix R greater than zero. Each non-zero eigenvalue in matrix is associated with a column eigenvector in matrix . The eigenvector matrix has the property that
(2.10)
where is the identity matrix with ones in the principal diagonal and zeroes elsewhere. simply indicates that the cross of any two eigenvector are 0 and the sum of squares of the elements for a given eigenvector are equal to 1. This means that eigenvector are uncorrected over space, that is, they are orthogonal to one another. Each eigenvector represents the spatial EOF pattern of mode (it has dimension , that is, the number of locations in the original data).