The S value . . . and other stories
BMJ 2020; 370 doi: https://doi.org/10.1136/bmj.m3020 (Published 06 August 2020) Cite this as: BMJ 2020;370:m3020
Taken by surprise
Despite widespread criticism of significance testing, doctors, scientists, and journal editors continue to use P values as a way of dichotomising studies into significant or non-significant, positive or negative. Two articles in the American Journal of Epidemiology explain why this is misleading and suggest that we should try using the S value instead. The S value measures the degree to which the observed data are surprising using a scale that is the equivalent to the number of consecutive coin flips all coming up heads (Am J Epidemiol doi:10.1093/aje/kwaa136; doi:10.1093/aje/kwaa137).
Sounds of sickness
Some coughs are characteristic of a particular infection—whooping cough or the seal-like bark of children with croup, for example—but most coughs don’t announce their cause so clearly. Paid volunteers were played audio clips of coughs or sneezes and asked if the sounds they heard were produced …
Log in
Log in using your username and password
Log in through your institution
Subscribe from £184 *
Subscribe and get access to all BMJ articles, and much more.
* For online subscription
Access this article for 1 day for:
£50 / $60/ €56 (excludes VAT)
You can download a PDF version for your personal record.