PubMed · 1609181
Strengthening some common multiple test procedures for discrete data.
Abstract
This paper proposes modification of some commonly used multiple test procedures for testing problems that arise when the underlying distributions are discrete. These procedures have been shown as conservative because the exact nominal levels are unattainable. The amended procedures can achieve actual type I errors much closer to the nominal levels, thus giving rise to more powerful tests.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
D M Rom. 1992-02-28. Strengthening some common multiple test procedures for discrete data.. https://doi.org/10.1002/sim.4780110413
Cite the original work for its findings. Save a collection to share your selection of sources.