Statistical association issues statement to clarify use of p-values
DOI: 10.1063/PT.5.029639
Nature : The scientific community is rethinking the p-value, which traditionally has been considered the gold standard of statistical validity . A new statement from the American Statistical Association (ASA) claims that the continued reliance on and misuse of p-values is “contributing to the number of research findings that cannot be reproduced.” Although researchers tend to interpret p-values of 0.05 or less as indicative of a statistically significant correlation between variables, that is not always true. Scientists also tend to wrongly equate p-values with the importance of a finding. The ASA statement spells out six principles intended to improve the interpreting and communicating of statistical methods in research.