Implications of statistical tests of variance and means

The primary purpose of this paper is to illustrate that tests for the homogeneity of variance in the statistical analysis of clinical neuropsychological data may provide unique information. Specifically, tests of variance homogeneity are more sensitive to outliers than the more commonly used tests of group means. Moreover, when both a test of means and of variance are done and the results compared, the nature of the deficit within the sample can be interpreted with greater confidence.