How to Explain the Recent Reversal on the P-Value Approach to Clients Who Are Not Statistical Experts

• Activity Number: 94 - Section on Statistical Consulting P.M. Roundtable Discussion
• Type: Roundtables
• Date/Time: Monday, August 3, 2020 : 12:00 PM to 1:00 PM
• Sponsor: Section on Statistical Consulting
• Author(s): Alexandra Kapatou*
• Companies: American University
• Keywords: p-value; effect; statistical thinking

Abstract

On June 2016, the ASA published in the American Statistician a statement titled “The ASA's Statement on p-Values: Context, Process, and Purpose” [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]. This statement was addressed mostly to statisticians and professionals with extensive knowledge of statistics, so the concepts presented were therefore probabilistic in nature and difficult to understand by the average person. Do statisticians really object to using the p-value approach? In this round table, we will discuss how to explain these difficult concepts to a client who is not a statistical expert, yet she is curious and wants to learn what the fuss is all about. If time permits, we may discuss other related issues, such as confusing small p-values and large effects. Then, we will open the floor to the attendees to lead the discussion with their concerns and comments.