The false positive risk: a proposal concerning what to do about p values

TL;DR

This paper discusses the widespread issue of false positives in biomedical research due to overreliance on p values and proposes using false positive risk as an additional, more reliable measure of evidence strength.

Contribution

It introduces the concept of false positive risk as an easy-to-understand supplement to p values and confidence intervals to improve the reliability of scientific conclusions.

Findings

P values often underestimate the false positive risk.

Adding false positive risk helps better interpret statistical evidence.

Proposes practical guidelines for implementing false positive risk in research.

Abstract

It is widely acknowledged that the biomedical literature suffer from a surfeit of false positive results. Part of the reason for this is the persistence of the myth that observation of a p value less than 0.05 is sufficient justification to claim that you've made a discovery. It is hopeless to expect users to change their reliance on p values unless they are offered an alternative way of judging the reliability of their conclusions. If the alternative method is to have a chance of being adopted widely, it will have to be easy to understand and to calculate. One such proposal is based on calculation of false positive risk. It is suggested that p values and confidence intervals should continue to be given, but that they should be supplemented by a single additional number that conveys the strength of the evidence better than the p value. This number could be the minimum false positive risk (that calculated on the assumption of a prior probability of 0.5, the largest value that can be assumed in the absence of hard prior data). Alternatively one could specify the prior probability that it would be necessary to believe in order to achieve a false positive risk of, say, 0.05.