The Mood-Westenberg and Siegel-Tukey tests were examined to determine their robustness with respect to Type-I error for detecting variance changes when their assumptions of equal means were slightly violated, a condition that approaches the Behrens-Fisher problem. Monte Carlo methods were used via 34,606 variations of sample sizes, α levels, distributions/data sets, treatments modeled as a change in scale, and treatments modeled as a shift in means. The Siegel-Tukey was the more robust, and was able to handle a more diverse set of conditions.
Lowenstein, L. C. & Sawilowsky, S. S. (2017). Robustness and power comparison of the Mood-Westenberg and Siegel-Tukey tests. Journal of Modern Applied Statistical Methods, 16(1), 195-232. doi: 10.22237/jmasm/1493597460