What is it about?
To control the overall probability of a false positive result when testing multiple hypothesis, an appropriate multiple testing procedure has to be applied. A robust and widely used multiplicity adjustment is the Bonferroni test. However, this test is typically conservative resulting in an increase of false negative findings. In this paper we develop a new approach to adjust for multiple testing, that leads to less false negative findings and on average requires lower sample sizes.
Photo by Stephen Dawson on Unsplash
Why is it important?
Adjustment for multiple testing is essential in empirical research to support the generalization and reproducibility of findings. The proposed multiple test leads to more efficient study designs with larger power to detect signals in the data while reducing the required expected number of replications or subjects.
Read the Original
This page is a summary of: A Uniform Improvement of Bonferroni-Type Tests by Sequential Tests, Journal of the American Statistical Association, March 2008, Taylor & Francis, DOI: 10.1198/016214508000000012.
You can read the full text:
The following have contributed to this page