Discussion: View Thread

To help us improve statistical and scientific communication, we hope to enlist support for the use of "statistically discernible." If publishers, and others, learn that statisticians are supportive of this idea, then they might help us move the profession in this direction. Please indicate how strongly you agree or disagree with the statement in our short 3-question survey at this link: https://forms.gle/ynK57RFJAs6pypG99. Please also provide any additional comments. (Your email address will not be recorded.)

We know that “significant” does not mean “important,” but our students and others do not. Our solution to the problem of misunderstanding of “statistically significant” is to call a result “statistically discernible” rather than “statistically significant.” If the p-value is small, it means that the test was able to discern a difference (although this might be a Type I error…). Of course, with a large enough sample size, any small treatment effect will lead to a small p-value. The sample size acts like a magnifying glass, giving us the power to find a difference even when that difference is quite modest. So if our sample is large enough, we can discern a difference. — Jeff Witmer (2019), Journal of Statistics Education Editorial

Are you wondering how you can get started making the switch to "discernible"? You'll find some boilerplate text you can copy and modify in your publications, presentations, responses to referees and reviewers, grants, etc. in these publications:

• Jeff Witmer Editor-in-Chief (2019) Editorial, Journal of Statistics Education, 27:3, 136–137, DOI: 10.1080/10691898.2019.1702415
• EJ Daza, Ditch “Statistical Significance” — But Keep Statistical Evidence | How? A statistician shares a writing sample. Towards Data Science, 14 June 2021.

Here's the link to the survey again (previewed): Discerning Statistical from Scientific Communication