News for hackers. Stuff that matters.

A comment on Redefine statistical significance. Parent comment

Re:Redefine statistical significance by mhermher on Thursday September 07, 2017 @02:47PM (#15194678)
This is why I think better multiple-test-correction methods are more important and would lead better to a desirable outcome than just lowering alpha.
[ Parent | on HN ]
Re:Redefine statistical significance by stewbrew on Friday September 08, 2017 @03:32AM (#15198485)
Multiple-test correction usually implies lowering alpha, doesn't it?
[ Parent | on HN ]
Re:Redefine statistical significance by mhermher on Friday September 08, 2017 @03:51PM (#15203412)
For any given test yes, but it usually tries to maintain your overall alpha at the same level.
[ Parent | on HN ]