Back to Search
Start Over
A bootstrap test for equality of variances
- Source :
-
Computational Statistics & Data Analysis . Oct2010, Vol. 54 Issue 10, p2306-2316. 11p. - Publication Year :
- 2010
-
Abstract
- Abstract: We introduce a bootstrap procedure to test the hypothesis that variances are homogeneous. The procedure uses a variance-based statistic, and is derived from a normal-theory test for equality of variances. The test equivalently expressed the hypothesis as , where ’s are log contrasts of the population variances. A box-type acceptance region is constructed to test the hypothesis . Simulation results indicated that our method is generally superior to the Shoemaker and Levene tests, and the bootstrapped version of the Levene test in controlling the Type I and Type II errors. [Copyright &y& Elsevier]
Details
- Language :
- English
- ISSN :
- 01679473
- Volume :
- 54
- Issue :
- 10
- Database :
- Academic Search Index
- Journal :
- Computational Statistics & Data Analysis
- Publication Type :
- Periodical
- Accession number :
- 51130925
- Full Text :
- https://doi.org/10.1016/j.csda.2010.04.012