Skip to main content
Research article, 2006

Statistical inference for the coe??cient of variation in normally distributed data

Forkman Johannes, von Rosen Dietrich


Methods for analysing coefficients of variation in normally distributed data are studied. An approximate F-test for equality of two coefficients of variation is introduced. The approximate F-test is compared with eight other tests in a simulation study. The new test performs well, also when the sample sizes are small. A generalized version of the approximate F-test is defi??ned for the case that there are several independent estimates of each coeffi??cient of variation, calculated with different averages. The test is applied to a real immunoassay dataset from diagnostic research. All moments of the proposed test statistic are shown to be approximately equal to the moments of an F-distribution. The distribution of the logarithm of the test statistic equals the distribution of the logarithm of an F- distribution plus some error variables that are in probability of small orders


coefficient of variation; normal distribution; McKay's approximation; approximate F-test

Published in

Research report (Centre of Biostochastics)
2006, number: 2, pages: 1-29
Publisher: Centre of Biostochastics, SLU