News for hackers. Stuff that matters.
Re:It’s not just p=0.048 vs. p=0.052 by tgb on Wednesday September 11, 2019 @05:11PM (#20944761)
Compound/interval null hypotheses basically solve this effect-size problem and probably should be used more.
Re:It’s not just p=0.048 vs. p=0.052 by BenoitEssiambre on Wednesday September 11, 2019 @05:22PM (#20944854)
Yes, it should be required.