Abstract
A comparison was made between seven different procedures used to determine variance homogeneity. The seven tests that were chosen for this comparison are Bartlett's test, Levene's test (mean), Levene's test (median), Levene's test (trimmed mean), the O'Brien test, the Cochran test, and Fligner's test. Data were simulated to compare the procedures using different distributions (Normal, Beta, and Uniform), sample sizes (5, 10, 50, and 100), equal samples (n_1 = n_2=...=n_k), and five (5) levels (i.e., k = 5). The power of the test and type l error rate were used to compare the selected procedures at a significant level of 0.05. The findings of the comparison showed that the Fligner technique is superior to all other procedures when the dataset is normally distributed. On the other hand, the Bartlett procedure is superior regardless of sample size when the dataset is not normally distributed.