Statistical inference for a ratio of dispersions using paired samples

Wilcox (1990) examined the Type I and Type II error rates for several robust tests of H-0: sigma(1)(2)/sigma(2)(2) = 1 in paired-data designs and concluded that a satisfactory solution does not yet exist. A confidence interval for a ratio of correlated mean absolute deviations is derived and performs well in small sample sizes across realistically nonnormal distributions. When used to test a hypothesis, the proposed confidence interval is almost as powerful as the most powerful test examined by Wilcox.