Indication of Measures of Uncertainty for Statistical Significance in Abstracts of Published Oncology Trials
Author(s) -
Samuel M. Rubinstein,
Elizabeth A. Sigworth,
Shervin Etemad,
Richard Lewis Martin,
Qingxia Chen,
Jeremy L. Warner
Publication year - 2019
Publication title -
jama network open
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 3.278
H-Index - 39
ISSN - 2574-3805
DOI - 10.1001/jamanetworkopen.2019.17530
Subject(s) - medicine , context (archaeology) , logistic regression , clinical trial , odds ratio , statistics , randomized controlled trial , oncology , mathematics , biology , paleontology
Key Points Question Do the abstracts of oncology randomized clinical trials with results of marginal statistical significance express uncertainty, and what characteristics are associated with uncertainty expression? Findings This systematic review and meta-analysis of 556 phase 3 randomized clinical trials found that most of the abstracts do not fully express uncertainty, and that uncertainty expression decreases when the P value surrounding a result is below its prespecified α level. The expression of uncertainty appears to be increasing over time. Meaning It appears that a P value below the prespecified α level is often treated as a discrete threshold for statistical significance in publication of randomized clinical trials.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom