The Use of "Trend" Statements to Describe Statistically Nonsignificant Results in the Oncology Literature

Kevin T Nead; Mackenzie R Wehner; Nandita Mitra

doi:10.1001/jamaoncol.2018.4524

The Use of "Trend" Statements to Describe Statistically Nonsignificant Results in the Oncology Literature

JAMA Oncol. 2018 Dec 1;4(12):1778-1779. doi: 10.1001/jamaoncol.2018.4524.

Authors

Kevin T Nead¹, Mackenzie R Wehner², Nandita Mitra³

Affiliations

¹ Department of Radiation Oncology, Perelman School of Medicine at the University of Pennsylvania, Philadelphia.
² Department of Dermatology, Perelman School of Medicine at the University of Pennsylvania, Philadelphia.
³ Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine at the University of Pennsylvania, Philadelphia.

Abstract

This study examines recent original research articles in leading oncology journals to evaluate the use of statements about the trend of a P value toward significance to describe statistically nonsignificant results.

MeSH terms

Bias
Bibliography of Medicine*
Bibliometrics
Data Interpretation, Statistical*
Humans
Medical Oncology / methods
Medical Oncology / standards*
Medical Oncology / statistics & numerical data
Publications / standards
Publications / statistics & numerical data
Terminology as Topic*

Grants and funding

T32 AR007465/AR/NIAMS NIH HHS/United States