Open AccessInterpreting trial results—time for confidence and magnitude and not P values please
Author(s) -
Jonathan C. Craig
Publication year - 2018
Publication title -
kidney international
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 3.499
H-Index - 276
eISSN - 1523-1755
pISSN - 0085-2538
DOI - 10.1016/j.kint.2018.11.006
Subject(s) - magnitude (astronomy) , confidence interval , statistics , medicine , mathematics , physics , astronomy
The problems with the P value as the single metric to summarize the results of a study are being recognized. It captures a single domain-random error-but it is relatively uninformative about more critical domains for deciding whether the results should be applied to clinical care and policy. Alternatives include the components of the outcomes reported (relevance, magnitude, frailty, and net benefit) and confidence (risk of bias and directness).
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