On the Application of the Transformation to Testing the Coeffcient of Variation
(English)Manuscript (preprint) (Other academic)
It is difficult to drive mathematically the theoretical sampling distribution of the coefficientof variation (CV) and to make inferences about it. This paper attempts to provide an overview ofa parametric asymptotic inference of the coefficient of variation using a transformation that gives variancestabilization. Although it can easily be shown that the variance of the logarithm of the sample mean is approximatelythe coefficient of variation, up to now it has not been demonstrated how this idea can be used to draw inferences concerningthe CV. This article shows how the bootstrap method can be used to improve the discussed methods and deals with one- andtwo-sample tests of the CV.
Asymptotic method; Bootstrap method; Coefficient of variation; Jackknife; Variance-stabilizing transformation; Variance test
Probability Theory and Statistics
Research subject Statistics
IdentifiersURN: urn:nbn:se:uu:diva-158979OAI: oai:DiVA.org:uu-158979DiVA: diva2:441928