Comparing variances of correlated variables

DOI10.1007/BF02294062MaRDI QIDQ1089702zbMATH OpenOpenAlexFDO

Authors Ayala Cohen

Publication date 1986

Published in Psychometrika (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/bf02294062

zbMATH Keywords

bootstrap procedurecombinations of sample sizescorrelated variablescorrelation structureequality of the variancesFisher's z-transformlevelnonnormal datanormally distributed variablesPitman's testpowerrobustness

Mathematics Subject Classification ID

Parametric hypothesis testing (62F03) Robustness and adaptive procedures (parametric inference) (62F35) Hypothesis testing in multivariate analysis (62H15) Applications of statistics to psychology (62P15)

Review text

A test is proposed for the equality of the variances of \(k\geq 2\) correlated variables. Pitman's test for \(k=2\) reduces the null hypothesis to zero correlation between their sum and their difference. Its extension, eliminating nuisance parameters by a bootstrap procedure, is valid for any correlation structure between the k normally distributed variables. A Monte Carlo study for several combinations of sample sizes and number of variables is presented, comparing the level and power of the new method with previously published tests. Some nonnormal data are included, for which the empirical level tends to be slightly higher than the nominal one. The results show that our method is close in power to the asymptotic tests which are extremely sensitive to nonnormality, yet it is robust and much more powerful than other robust tests.

Recommendations

• Comparing the variances of two dependent variables
• scientific article; zbMATH DE number 1031949
• Testing and estimation of equal variances for correlated variables
• Comparing the variances or robust measures of scale of two dependent variables
• Testing for Correlated Errors in the Analysis of Variance
• Multiple comparison for checking correlations among several normal random variables

Cites work

• A NOTE ON NORMAL CORRELATION
• A PROCEDURE FOR TESTING THE EQUALITY OF p CORRELATED VARIANCES
• Bootstrap methods: another look at the jackknife
• Bootstrap tests and confidence regions for functions of a covariance matrix
• scientific article; zbMATH DE number 3141625 (Why is no real title available?)
• scientific article; zbMATH DE number 3782216 (Why is no real title available?)
• scientific article; zbMATH DE number 3458066 (Why is no real title available?)
• scientific article; zbMATH DE number 3036187 (Why is no real title available?)
• scientific article; zbMATH DE number 3059914 (Why is no real title available?)
• NON-NORMALITY AND TESTS ON VARIANCES
• Robust Estimation of Dispersion Matrices and Principal Components
• Simulated power functions

Cited in

(12)

• An equality test for variances of two complex correlated Gaussian processes
• Hypotheses testing for comparing means and variances of correlated responses in the symmetric non-normal case
• On Testing Homogeneity of Variances of Correlated Variables with Incomplete Data
• Tests for equality of dispersion in divariate samples- review and empirical comparison
• Comparing the variances of two dependent variables
• Bayes Factors for Testing Order Constraints on Variances of Dependent Outcomes
• On a correlated variance ratio distribution and its industrial application
• Confidence interval for a ratio of variances in bivariate nonnormal distributions
• How to Pretend That Correlated Variables Are Independent by Using Difference Observations
• Testing and estimation of equal variances for correlated variables
• A \(p\)-value for testing the equivalence of the variances of a bivariate normal distribution
• On direction of dependence

This page was built for publication: Comparing variances of correlated variables

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1089702)