A more principled use of the p-value? Not so fast : a critique of Colquhoun's argument
Abstract
The usefulness of the statistic known as the p-value, as a means of quantifying the strength of evidence for the presence of an effect from empirical data has long been questioned in the statistical community. In recent years, there has been a notable increase in the awareness of both fundamental and practical limitations of the statistic within the target research fields and especially biomedicine. In this article, I analyse the recently published article (Colquhoun 2017 R. Soc. open sci.4, 171085 (doi:10.1098/rsos.171085)) which, in summary, argues that with a better understanding and thus more appropriate use of the statistic, many of the aforementioned limitations can be addressed. In particular, I demonstrate that the (often implicit) premises of this counterargument are questionable, in some cases arguably inconsistent, and that therefore the counterargument provides little if any justification for the continued use of the p-value. Additionally, my analysis should help researchers seeking to interpret their empirical data by illustrating the nuanced nature and the multiplicity of statistical, methodological and epistemological issues which must be considered in this process.
Citation
Arandelović , O 2019 , ' A more principled use of the p -value? Not so fast : a critique of Colquhoun's argument ' , Royal Society Open Science , vol. 6 , no. 5 , 181519 . https://doi.org/10.1098/rsos.181519
Publication
Royal Society Open Science
Status
Peer reviewed
ISSN
2054-5703Type
Journal article
Rights
Copyright © 2019 The Authors. Published by the Royal Society under the terms of the Creative Commons Attribution License http://creativecommons.org/licenses/by/4.0/, which permits unrestricted use, provided the original author and source are credited.
Collections
Items in the St Andrews Research Repository are protected by copyright, with all rights reserved, unless otherwise indicated.