Estuaries and Coasts Town Hall:

Misuse of P-values and why Estuaries and Coasts discourages the phrase statistically significant

Date: Thursday, 7 November
Time: 11:30 AM – 1:00 PM

For two decades, there has been a debate among statisticians about the misuse and misinterpretation of P-values. There is now a consensus among statisticians that it is wrong to use the binary choice of “statistically significant” or “non-significant” based on arbitrary assumptions about fixed alpha values e.g., 0.05 (Wasserstein et al. 2019), and some are recommending that editors ban the use of these terms from their journals (Hurlbert et al. 2019). The Estuaries and Coasts editors are considering this, but before taking such a drastic action, we want to explain to the CERF community what we are considering and why. This would both inform the CERF community that publishes in Estuaries and Coasts, provide advice on presenting results of statistical analyses, and allow the editors to receive feedback on how to move forward.

Please join us and bring your own lunch.


References

Hurlbert SH, Levine RA, Jessica Utts J (2019) Coup de Grâce for a tough old bull: “Statistically Significant” expires. The American Statistician 73(Sup1): 352-357. doi: 10.1080/00031305.2018.1543616

Wasserstein RL, Schirm AL, Lazar NA (2019) Moving to a world beyond “p < 0.05”, The American Statistician 73(Sup1): 1-19. doi: 10.1080/00031305.2019.1583913