2024
DOI: 10.1016/j.metip.2024.100140
|View full text |Cite
|
Sign up to set email alerts
|

Inconsistent multiple testing corrections: The fallacy of using family-based error rates to make inferences about individual hypotheses

Mark Rubin
Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2024
2024
2024
2024

Publication Types

Select...
5

Relationship

0
5

Authors

Journals

citations
Cited by 9 publications
(1 citation statement)
references
References 43 publications
0
1
0
Order By: Relevance
“…If at least one of the two constituent null hypotheses is rejected (while the significance level alpha 0.05 for each constituted test is adjusted by applying the Holm-Bonferroni correction), the union of their constituent alternative hypotheses is statistically significant, which means that the examined trait is statistically significant for the difference between the scribes and the reference group (where the family-wise error rate did not exceed the predefined significance level alpha). The establishment of the family of hypotheses follows Rubin’s paper 104 and the desired outcome of the analysis, which is the individual statistical significance of each trait. For these reasons, any other alpha adjustment would be redundant.…”
Section: Methodsmentioning
confidence: 99%
“…If at least one of the two constituent null hypotheses is rejected (while the significance level alpha 0.05 for each constituted test is adjusted by applying the Holm-Bonferroni correction), the union of their constituent alternative hypotheses is statistically significant, which means that the examined trait is statistically significant for the difference between the scribes and the reference group (where the family-wise error rate did not exceed the predefined significance level alpha). The establishment of the family of hypotheses follows Rubin’s paper 104 and the desired outcome of the analysis, which is the individual statistical significance of each trait. For these reasons, any other alpha adjustment would be redundant.…”
Section: Methodsmentioning
confidence: 99%