Online Program Home
My Program

Abstract Details

Activity Number: 74 - Challenges and Approaches to Teaching Statistics in the Health Sciences
Type: Contributed
Date/Time: Sunday, July 29, 2018 : 4:00 PM to 5:50 PM
Sponsor: Section on Teaching of Statistics in the Health Sciences
Abstract #330622 Presentation
Title: Statistical Significance: Time to Look Forward
Author(s): Philip Sedgwick*
Companies: St. George's, University of London
Keywords: Null hypothesis significance testing; P-values; Inference; Education; Teaching
Abstract:

Having become the cornerstone of research, Null Hypothesis Significance Testing (NHST) underpins decision making. Because of misunderstanding and misuse the validity of inferences based on NHST are questionable. Consequently, in 2015 the editors of a psychology journal took the radical decision to ban NHST, and ASA subsequently released a statement on its use and interpretation. Despite widespread discussion, little changed and journals continue to promote inference based on statistical significance. It is important that changes in practice continue to be advocated. This presentation will consider potential approaches including through education and the classroom. NHST is embedded in undergraduate courses and whilst some suggest it should not be taught, no magical alternative exists. It is suggested NHST is still taught, yet good practice encouraged. P-values provide useful information whilst NHST has practical applications in sample size calculations. Providing philosophical perspectives to research, and overviews of Fisher's and Neyman-Pearson's theories, permits the contrast of statistical with practical significance.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2018 program