Familywise type I error of ANOVA and ANOVA on ranks in factorial experiments

Abstract

This research evaluated the importance of a preliminary general analysis of variance (ANOVA) in the interpretation of data from factorial experiments under total nullity. For this, we evaluated the familywise type I error rate (accumulated FWER) of the F test for the unfolding of factorial ANOVA and factorial ANOVA on ranks, which were compared with the FWER for the global effect of treatments. In addition, we evaluated the FWER of the Tukey’s test under total nullity for factorial experiments in the presence or absence of preliminary ANOVA protection (omnibus F test). The study was conducted by simulating data from 2,000 experiments, which were separated into four representative agricultural research scenarios. For both the parametric factorial ANOVA and the non-parametric factorial ANOVA, the FWER significantly exceeded the nominal level of 5%, even under total nullity. While the tests that control the total FWER in the factorials are not being used, the factorial ANOVA should not be performed without the preliminary ANOVA F test showing a significant effect. This, of course, does not apply to tests that are not multiple comparisons, such as Bonferroni, Dunn-Sidak and others, which do not need ANOVA protection. The same recommendation applies to the factorial ANOVA on ranks.

Mechanical and Ballistic Properties of Epoxy Composites Reinforced with Babassu Fibers (Attalea speciosa)

“…With the variance result obtained (Table 5), it is necessary to calculate the F value, which is defined by comparing the variance in the calculations. This parameter is essential to assess the significance of differences between group means in the ANOVA [33]. The values of calculated F, p-value, and critical F are presented in Table 6.…”

Educational Advances in the Metaverse: Boosting Learning Through Virtual and Augmented Reality and Artificial Intelligence

“…ANOVA was also carried out to compare the learning results between different groups of users [58], [59]. This allows us to identify whether differences in teaching methods or system characteristics statistically impact student performance.…”

Delineamentos experimentais utilizados na avaliação da produção de leite

“…Esses experimentos não constituem propriamente um delineamento estatístico, mas um esquema orientado de desdobramento de graus de liberdade de tratamentos, podendo ser instalados em qualquer um dos delineamentos apresentados anteriormente. (Calegare, 2009;Carvalho et al, 2022).…”

“…Enquanto, o nível é considerado qualquer uma das subdivisões dentro do fator. Portanto, é de grande relevância em experimentos de arranjo fatorial, observar a interação entre os fatores que compõem as variáveis estudados, tais interações podem ser consideradas positivas ou negativas a depender dos níveis de combinação entre os fatores (Perecin & Filho, 2008;Carvalho et al, 2022).…”

“…O expoente indica o número de fatores e a base indica o número de níveis. Desta forma, um fatorial 2 2 tem dois fatores em dois níveis e um fatorial 3 2 tem dois fatores em três níveis (Carvalho et al, 2022).…”