(January 21, 2024 at 1:19 am)Nay_Sayer Wrote:(January 21, 2024 at 12:41 am)FlatAssembler Wrote: OK, let me try to summarize it even more: I think that I've calculated, using birthday calculations and collision entropy, that the probability of that k-r pattern in Croatian river names (Krka, Korana, Krapina, Krbavica, Kravarščica, 2*Karašica) occurring by chance is somewhere between 1/300 and 1/17.
But it could still be chance.
I'd hate for you to have wasted your time on this.
But the modern scientific method works via p-values. If, under the null hypothesis, the probability of some observation happening by chance is lower than 5%, you reject the null hypothesis.