Interval Estimation for the Difference of Two Independent Variances |
| |
| Authors: | Robert D Herbert Andrew Hayen Petra Macaskill Stephen D Walter |
| |
| Institution: | 1. The George Institute for Global Health , Sydney, NSW, Australia rherbert@george.org.au;3. Screening and Test Evaluation Program, School of Public Health , The University of Sydney , Sydney, Australia;4. Department of Clinical Epidemiology and Biostatistics , McMaster University , Hamilton, Ontario, Canada |
| |
| Abstract: | Analytical methods for interval estimation of differences between variances have not been described. A simple analytical method is given for interval estimation of the difference between variances of two independent samples. It is shown, using simulations, that confidence intervals generated with this method have close to nominal coverage even when sample sizes are small and unequal and observations are highly skewed and leptokurtic, provided the difference in variances is not very large. The method is also adapted for testing the hypothesis of no difference between variances. The test is robust but slightly less powerful than Bonett's test with small samples. |
| |
| Keywords: | Difference in variances F-test Homoscedasticity Heterogeneity of variances Kurtosis Levene's test |
|
|
