Should I adjust for multiple comparisons?
However, the probability of committing false statistical inferences would considerably increase when more than one hypothesis is simultaneously tested (namely the multiple comparisons), which therefore requires proper adjustment.
Why is Anova better than multiple t-tests?
Why not compare groups with multiple t-tests? Every time you conduct a t-test there is a chance that you will make a Type I error. An ANOVA controls for these errors so that the Type I error remains at 5% and you can be more confident that any statistically significant result you find is not just running lots of tests.
How is Bonferroni adjustment used for multiple comparisons?
Bonferroni adjustment Bonferroni adjustment is one of the most commonly used approaches for multiple comparisons (5). This method tries to control FWER in a very stringent criterion and compute the adjusted P values by directly multiplying the number of simultaneously tested hypotheses (m): p′i= min{pi × m, 1} (1 ≤ i ≤ m)
Can you conduct 10 independent ANOVAs for each dependent variable?
Think about it like that: you could conduct 10 independent ANOVAs for each of the 10 dependent variables (in case of only 2 groups ANOVA reduces to t-test, but it does not matter for this question). Then you would get 10 different p-values, and certainly would need to correct for multiple comparisons, e.g. by applying Bonferroni correction.
Do you need to correct for multiple comparisons in MANOVA?
Then you would get 10 different p-values, and certainly would need to correct for multiple comparisons, e.g. by applying Bonferroni correction. But if you use MANOVA, then you get only one single p-value and so there is no need for any corrections.
Which is the best adjustment method for multiple comparisons?
Bonferroni adjustment is one of the most commonly used approaches for multiple comparisons (5). This method tries to control FWER in a very stringent criterion and compute the adjusted P values by directly multiplying the number of simultaneously tested hypotheses (m): p′i= min{pi × m, 1} (1 ≤ i ≤ m)