Data Analytics Colloquium 11/11/2021 Speaker: Dr. Tse-min Lin “The p-Value Controversy” скачать в хорошем качестве

Data Analytics Colloquium 11/11/2021 Speaker: Dr. Tse-min Lin “The p-Value Controversy”

Abstract: The p-value controversy is not new. As early as 1970, Morrison and Henkel edited a reader titled The Significance Test Controversy (Aldine). The critiques of the Null Hypothesis Significance Test (NHST), however, did not prevent researchers in all disciplines from continuing to practice the methodology. The situation is different when the controversy reemerged in recent years: • In 2015, the editors of Basic and Applied Social Psychology (BASP) announced that the journal would no longer publish papers containing P values because the statistics were too often used to support lower-quality research. • In 2016, the American Statistical Association issued a statement, “The ASA's Statement on p-Values: Context, Process, and Purpose” to advice caution on interpreting and using p-value tests. (Ronald L. Wasserstein & Nicole A. Lazar, The American Statistician, Volume 70, 2016 - Issue 2). • In 2017, a group of 72 researchers published a paper, “Redefine Statistical Significance,” proposing a change from α=0.05 to α=0.005 as the level of significance. (Benjamin et al., Nature Human Behaviour, 01 September 2017). • In 2018, Political Analysis banned p-values: “Political Analysis will no longer report p values in regression tables or elsewhere. There are many reasons for this change—most notably that a p value alone does not give evidence in support of a given model or the associated hypotheses.” (Political Analysis, Tweet, January 22, 2018) It subsequently took one step back: “However, in the case of design based experiments and related procedures (permutation tests, asymptotic approximations, etc.) p-values are appropriate and may be supplied. (Political Analysis, “Instructions for Contributors”) • In 2018, a group of 88 researchers responded to the call to redefine statistical significance with “Justify Your Alpha”. (Lakens et al., Nature Human Behaviour, 26 February 2018.) • In 2019, Nature published an article, “Scientists Rise up against Statistical Significance,” by V. Amrhein, S. Greenland, B. McShane, and 800+ signatories calling for “a stop to the use of p values in the conventional, dichotomous way.” (Amrhein et al., Nature, 20 March 2019). This lecture will review these developments, explain the nature of the controversy, and summarize the alternative approaches that have been suggested.