Saddlepoint approximations for tests of dispersion

Abstract

The nonparametric class of tests for dispersion is widely used for testing the equality of the scale parameters of two populations. This class includes Mood, Siegel-Tukey, Klotz and Moses tests. This paper uses the double saddlepoint approximation to calculate analytical mid-p-values for these tests that are almost exact as the permutation simulation method. The performance of the saddlepoint method is assessed using an extensive simulation study. The speed and accuracy of the saddlepoint method enable us to invert the dispersion tests to calculate (1 - α)100% confidence intervals for the dispersion parameter. © 2012 Springer-Verlag.