One outcome of the Monte Carlo study is that rank-based analyses based on shape parameters in a neighborhood of the correct α had very similar behavior to that using the correct α.
Only p values smaller than the corrected α were considered statistically significant.
The corrected α level for the number of tests performed (159) was estimated at 0.0003.
ANOVA was used to compare values among different groups, and least significant difference tests were used to identify specific differences between the two groups using corrected α values.
Using a corrected α of 0.05/60 = 0.00083 for the first test, 15 relationships were found to be significant.
Using a corrected α of 0.05/401 = 0.000124 for the first test, 61 changes were still significant, or a mean of 2.2 changes per case [Table 2, Fig. 2].
For testing two hypotheses, being a 35% difference in response rate between the morphine group vs. the fentanyl group and a 35% difference in response rate between the oxycodone group vs. the fentanyl group, we used a corrected α of.025 instead of.05.
Using a Bonferroni corrected α of 0.008 0.05/66), a series of logistic regression analyses were performed to investigate if for any given age, the odds of identifying an incidental finding was different between sexes, for any of the six individual anatomic regions.
Mean standing leaf damage was significantly lower on S. macrophylla than all 10 other co-occurring species surveyed at Cabrits (unbalanced mixed-model ANOVA on log-transformed percent damage, with plot as the random factor, P<0.0001, F10, 180 = 9.22; planned post-hoc comparisons of Swietenia vs. 10 native species using sequential-Bonferroni corrected α; Fig. 1).
As this finding was a result of systematically comparing anaplastic carcinomas with the other lesions, a Bonferroni correction for multiple testing was used (corrected α = 0.0083).
