6. Appropriate use and interpretation of the t statistic usingpooled variance require that the data satisfy thehomogeneity of variance assumption. This assumptionstipulates that the two populations have equal variances.An informal test of the assumption can be made byverifying that the two sample variances are approximatelyequal. Hartley’s F-max test provides a statisticaltechnique for determining whether the data satisfy thehomogeneity assumption. An alternative technique thatavoids pooling variances and eliminates the need for thehomogeneity assumption is presented in Box 10.2. 12