Methodological issues of using a class of neural networks called Mixture Density Networks (MDN) for discriminant analysis are discussed. MDN models have the advantage of having a rigorous probabilistic interpretation, and they have proven to be a viable alternative as a classification procedure in discrete domains. Both classification and interpretive aspects of discriminant analysis are discussed, and the approach is compared to the traditional method of linear discriminants as implemented in standard statistical packages. It is shown that the MDN approach performs well for both aspects. Many of the observations made are not restricted to the particular cases at hand, and are applicable to most applications of discriminant analysis in educational research. (Contains 31 references.) (Author/SLD)