The pretest-post design is a highly prestigious experimental design. A popular analytic strategy involves subjecting the data provided by this design to a repeated measures analysis of variance(ANOVA). Unfortunately, the statistical results yielded by this type of analysis can easily be misinterpreted, since the score model underlying the analysis is not correct. Two alternative strategies-gain scores and covariance-are discussed and compared. The advantage of a covariance approach to the data analysis becomes even clearer when one considers the researcher's alternative if the assumptions are found to be untenable. When the relationship the covariate and the dependent variable is not linear, the covariance model can be extended to include a quadratic or cubic component. The analysis of covariance was shown to be a more powerful technique with greater versatility with respect to available strategies for the situation in which assumptions are violated. Since a covariance analysis can do everything that a gain score analysis can do, but not vice versa, the covariance analysis is recommended for use in place of the repeated measures ANOVA.