800 scientist call out against statistical significance

post by Yoav Ravid 路 2019-03-23T12:57:01.989Z 路 LW 路 GW 路 1 comments

This is a link post for https://www.nature.com/articles/d41586-019-00857-9

Contents

1 comment

LessWrong has many [LW 路 GW]criticisms [LW 路 GW]of [LW 路 GW]P-values [LW 路 GW]/Statistical significance [LW 路 GW], And is often given as a coordination problem (or an inadequate equilibria).

In addition to the American Statistical Association - which, In 2016, 'released a statement in The American Statistician warning against the misuse of statistical significance and P values' - these authors now join the call too, with an article in nature signed by over 800 scientists. they write:

We are far from alone. When we invited others to read a draft of this comment and sign their names if they concurred with our message, 250 did so within the first 24 hours. A week later, we had more than 800 signatories.

What do you think will be the impact of it?

1 comments

Comments sorted by top scores.

comment by Douglas_Knight 路 2019-03-24T15:40:23.171Z 路 LW(p) 路 GW(p)

There have been a lot of such manifestos, so it will be pretty hard to isolate the effects of any particular one.

Such manifestos can be divided into two classes: those which set p-values in opposition to confidence intervals and those that describe them as the same. The first class has a positive suggestion: use confidence intervals. It seems to me that positive manifestos are more likely to be adopted than those which merely condemn p-values, but offer no alternative. This manifesto seems to condemn confidence intervals, but makes the very vague suggestion to pay attention to effect sizes. In the end, maybe that amounts to the same thing.