A comparison of the mixture and classification approaches to cluster analysis
Selvanayagam Ganesalingam, Geoffrey John McLachlan · Communication in Statistics- Theory and Methods · 1980
This paper examines the relative performance of two commonly used clustering methods based on maximum likelihood in the context of classifying a sample of observations of unknown origin arising from two normal populations with a common covariance matrix. the associated properties of the two methods are compared by conducting a series of simulation experiments under both mixture and separate sampling schemes.