Controlling the Type I error rate by using the nonparametric bootstrap when comparing means.

摘要: Of the several tests for comparing population means, best known are ANOVA, Welch, Brown-Forsythe, and James tests. Each performs appropriately only in certain conditions, none well every setting. Researchers, therefore, have to select appropriate procedure run risk of making a bad selection and, consequently, erroneous conclusions. It would be desirable test that any situation so obviate preliminary analysis data. We assess compare equality means simulation study, including non-parametric bootstrap techniques, finding ANOVA Brown-Forsythe exhibit similar exceptionally good behaviour.