Statistical significance should be abandoned, say scientistsBMJ 2019; 364 doi: https://doi.org/10.1136/bmj.l1374 (Published 25 March 2019) Cite this as: BMJ 2019;364:l1374
- Harriet Pike
Scientists writing in Nature have called for the concept of statistical significance to be abandoned, a move backed by the American Statistical Association.
Valentin Amrhein, a professor of zoology at the University of Basel, Switzerland, and colleagues argued that researchers often apply P values incorrectly and use them to draw unhelpful conclusions. “The false belief that crossing the threshold of statistical significance is enough to show that a result is ‘real’ has led scientists and journal editors to privilege such results, thereby distorting the literature,” they wrote in Nature.1
The authors said that researchers should never conclude that there is “no difference” or “no association” between two results just because a P value is larger than a threshold such as 0.05 or because a confidence interval includes …