Testing multiple-group variance equality with randomization procedures

The operating characteristics of different statistical tests for evaluating multiple-group variance equality were examined using a simulation study. Normal-theory tests including Bartlett's test, Levene's test and Hartley's test were compared to randomization tests in this study. The randomization tests maintained nominal Type I error rates over a variety of conditions. Levene's test was conservative under all conditions examined. Both Bartlett's test and Hartley's test were anti-conservative ( rejects more frequently than nominally specified) when the distribution was lighter-tailed than a normal distribution ( double exponential) and were conservative when the distribution was heavier-tailed than a normal distribution ( uniform). Bartlett's test performed exceptionally well when the distribution was normal. Use of randomization test is recommended as a test of variance equality as this test performed at nominal Type I error rates and exhibited better power properties than Levene's test, the other test that controlled Type I error rates ( albeit conservatively).