Discriminant Functions When Covariance Matrices are Unequal

摘要: Abstract This study compares by Monte Carlo methods the performance of three discriminant functions in classifying individuals into two multivariate normally distributed populations when covariance matrices are unequal—the quadratic, best linear and Fisher's function. The comparison is carried out both asymptotically using samples. expected value probabilities used as measure performance. Parameters that varied include distance between populations, matrices, number dimensions, samples size a priori origin from populations.