Rao's Distance between Normal Populations That Have Common Principal Components
W. J. Krzanowski · Biometrics · 1996
SUMMARY A theoretical derivation is provided of Rao's distance between two normal populations that have different means and whose dispersion matrices satisfy the 'common principal component model.' According to this model, the dispersion matrices share the same eigenvectors but are permitted to have arbitrary eigenvalues. This structure is useful for modeling a variety of real data sets, so the theoretical result has important practical implications. It is illustrated on a biometric data set.