SciELO - Scientific Electronic Library Online

 
vol.32 issue1Rhizobacteria to control cotton bacterial blightFiber content and yield grain in common bean populations author indexsubject indexarticles search
Home Pagealphabetic serial listing  

Ciência e Agrotecnologia

Print version ISSN 1413-7054

Abstract

SILVA, Roberta Bessa Veloso; FERREIRA, Daniel Furtado  and  NOGUEIRA, Denismar Alves. Robustness of asymptotic and bootstrap tests for multivariate homogeneity of covariance matrices. Ciênc. agrotec. [online]. 2008, vol.32, n.1, pp. 157-166. ISSN 1413-7054.  http://dx.doi.org/10.1590/S1413-70542008000100023.

The present work emphasizes the importance of testing hypothesis on homogeneity of covariance matrices from multivariate k populations. The violation of the assumption of the homogeneity of covariance matrices affects the performance of the tests and the coverage probability of the confidence regions. This work intends to apply two tests of homogeneity of covariance and to evaluate type I error rates and power using Monte Carlo simulation in normal populations and robustness in non normal populations. Multivariate Bartlett's test (MBT) and its bootstrap version (MBTB) were used. Different configurations are tested combining sample sizes, number of variates, correlation and number of populations. Results show that the bootstrap test was considered superior to the asymptotic test and robust, since it controls the type error I rate.

Keywords : Simulation; type I error rate; power, Monte Carlo.

        · abstract in Portuguese     · text in English     · pdf in English