The use and abuse of p-values has been a major discussion topic in statistics and the wider scientific community, precipitated by the decision of Basic and Applied Social Psychology1 to ban p-values, and followed up by the ASA Statement on Statistical Significance and p-Values2. This has led to many debates about how (and how not) to interpret and use p-values. Among many assessments that the uncritical application of p-values in the scientific literature is causing a problem with reproducibility, the debate about the best ways to present statistical evidence to replace this established practice is more fragmented.
The Royal Statistical Society plans to hold a Discussion Meeting on 'practical alternatives to p-values' in 2019 and is now inviting submissions for inclusion in the programme for the meeting. The assessment and summarisation of statistical evidence is important in a wide range of subject areas, and we welcome submissions from all of these, and other, philosophical perspectives. Theoretical developments are also welcomed, as long as they address the theme through practical applicability.
Discussion Meetings, formerly known as Ordinary Meetings, consist of one or more papers that are presented orally and subsequently published in one of the series of the Journal of the Royal Statistical Society together with all contributions to the discussion at the meeting itself, or submitted in writing shortly afterwards. All submitted papers are refereed, both for their scientific quality and their potential to generate discussion. Papers that meet the first criterion but not the second may, with the agreement of the authors, be referred to the editors of the Journal with a view to direct publication.
We anticipate that this will be a multi-paper meeting, for which individual papers will probably be substantially shorter than is typical for a single-paper meeting3. For this reason, we are adopting a staged approach to the review process, as follows:
- Full paper submission. The Society’s Discussion Meetings Committee will consider all abstracts received by 9 July and will invite full paper submissions from a selection of these. Invited authors will be asked to submit their papers by Friday 30 November 2018.
- Refereeing. All invited papers received by 30 November 2018 will be refereed using the Society’s standard criteria for discussion meeting papers (scientific quality and discussability), and a selection will be chosen to make up a multi-paper meeting.
- We anticipate that the meeting will take place at the RSS’s conference in early September 2019 (although this is subject to confirmation).
Discussion Papers Editor, Journals of the Royal Statistical Society
Ronald L. Wasserstein & Nicole A. Lazar (2016) The ASA's Statement on p-Values: Context, Process, and Purpose, The American Statistician, 70:2, 129-133, DOI: 10.1080/00031305.2016.1154108