The issues in the interpretation of discriminant analyses presented are restricted to the typical uses of discriminant analysis by behavioral science researchers. Because behavioral researchers use computer programs packages, the issues discussed deal with information obtainable from the package discriminant analysis programs. The following issues are reviewed: (1) distinguishing between a linear discriminant function and a linear classification function; (2) misusing a stepwise discriminant analysis program; (3) ordering variables and selecting variable subsets; (4) choosing a classification rule; (5) estimating true classification hit rates; (6) assessing classification accurately; and (7) examining and using classification results. (Author/PN)