Type I error for the F-statistic, Greenhouse-Geisser (F-GG) and Huynh-Feldt (F-HF) adjustments, and boostrap-F (B-F) in split-plot design Authors: M. J. Blanca, R. Alarcón, R. Bono, J. Arnau, F. J. García-Castro, and G. Vallejo D: Distribution. Shape of the distribution. The numbers indicate the values of skewness (?1) and kurtosis (?2), respectively. The normal distribution and four non-normal distributions are used: slight (?1 = .4, ?2 = .8), moderate (?1 = 1, ?2 = 1.5), severe (?1 = 1.41, ?2 = 3), and extreme (?1 = 2.31, ?2 = 8) deviation from normality. VR: Ratio of the covariance matrices between the two groups: a) homogeneity of variance, 1:1; b) heterogeneity of variance, 1:1.5, 1:2, and 1:5. In this scenario, the covariance matrix of the second group could be, respectively, 1.5, 2 or 5 times larger than that of the first group. P: Pairing of variance with group sample size. The pairings used were: null (0) when there are equal group sizes; positive (+) when the largest group size is associated with the largest value of variance; and negative (-) when the largest group size is associated with the smallest variance. N: Total sample size: 20, 40, 60, 80, 100, 150 and 200. ?n: Coefficient of sample size variation (?n). Represents the amount of inequality in group sizes and was calculated by dividing the standard deviation of the group size by its mean. The values of ?n were 0 (balanced design), 0.16 (low value), 0.33 (medium value) and 0.50 (high value). n1, n2: Sample size of group 1 and group 2, respectively. e: Greenhouse-Geisser epsilon estimation (e ^). The values were .50, .60, .70, .80, .90 and 1. F g: Type I error of the F-statistic for group effect. B-F g: Type I error of boostrap-F for group effect. F t: Type I error of the F-statistic for time effect. F-GG t : Type I error of the Greenhouse-Geisser adjustment for time effect. F-HF t: Type I error of the Huynh-Feldt adjustment for time effect. B-F t: Type I error of boostrap-F for time effect. F g x t: Type I error of the F-statistic for group x time interaction. F-GG g x t: Type I error of the Greenhouse-Geisser adjustment for group x time interaction. F-HF g x t: Type I error of the Huynh-Feldt adjustment for group x time interaction. B-F g x t: Type I error of boostrap-F for group x time interaction.