The Mann–Whitney-U-test and for multiple comparisons the Kruskal Wallis-ANOVA was used.
To account for multiple comparisons the threshold for significance was p < 0.003.
After correcting for multiple comparisons, the distributions of these CNVs were still significantly different (all P = 0.037) (Table S5).
To address the issue of multiple comparisons, the statistical maps were thresholded at P < 0.001 (voxel level) and FWE corrected to P < 0.05 at the cluster level.
After analyzing the sizes of the S-layer proteins of these three genotypes for multiple comparisons, the results demonstrated the significant differences between these strains (Fig. 4).
To take into account the type I error inflation generated by multiple comparisons, the Bonferroni correction was applied (new threshold for type I error <5 %: P < 0.0019).
To correct for multiple comparisons, the Bonferroni correction was applied.
For multiple comparisons, the significance level was adjusted using Bonferroni correction.
In the case of potential multiple comparisons, the p-values were corrected with the Bonferroni correction.
For potential multiple comparisons, the p-values were corrected with the Bonferroni correction.
Had we adjusted for multiple comparisons, the observed differences would not have reached statistical significance.
