Generalización del enfoque Brown-Forsythe a diseños factoriales

摘要: Generalization of the Brown-Forsythe approach to factorial designs. The current paper proposes a solution that generalizes ideas Brown and Forsythe problem comparing hypotheses in twoway classification designs with heteroscedastic error structure. Unlike standard analysis variance, proposed does not require homogeneity assumption. A comprehensive simulation study, which sample size cells, relationship between cell sizes unequal degree variance heterogeneity, population distribution shape were systematically manipulated, shows approximation was generally robust when normality heterogeneity jointly violated.