Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Statisticians want to abandon science’s standard measure of ‘significance’

sciencenews.org

Post reply on HN
Print view View original

141–142 of 142 posts

Re: Statisticians want to abandon science’s standard measure of ‘significance’

#141

Post by wnoise »

Filligree wrote: post #139
wnoise wrote: post #107

Earlier quoted context omitted.

Well, you can report odds ratios (or their log).

That's good advice in general, but doesn't really answer the question of "How likely is it?".

Right, because you can't answer that without prior information. Log-odds is a step towards giving a function of prior information (but it is limited to the actual class of hypotheses investigated).

Re: Statisticians want to abandon science’s standard measure of ‘significance’

#142

Post by dekimir »

kerkeslager wrote: post #16

If you're looking for a replacement you don't understand the problem. The problem isn't that P=.05 is an arbitrary measure of significance. The problem is that only publishing significant results is a bias against the null hypothesis . Let's say you're doing a study of flipping coins. The null hypothesis is that the coin is evenly weighted. If the null hypothesis is true, when you flip a coin once, it will come up he…

This explanation is so brilliant that I created a short URL pointing to it: https://cutit.org/AJCFS
Post reply on HN