00:12
When accompanied by "my professor said I have to do a Mann-Whitney but none of my results are significant" ... what can you say? "Next time, ask someone who knows what power is about your experimental design before collecting data" seems a little rude but perhaps it's a situation where some kind of rude shock may be called for.
3
If you're comparing p-values with a 5% significance level and use a two-tailed nonparametric test (it won't matter which one) with n1=3 and n2=3, the power is literally 0 in that situation. Their professor just got them to waste time and money (and some cases, to pointlessly distress some creatures into the bargain)
21 hours later…
« first day (3276 days earlier) ← previous day next day → last day (2027 days later) »