Evidence-based research: understanding the best estimate
Authors Bauer J, Spackman S, Fritz R, Bains A, Jetton-Rangel J
Received 1 June 2016
Accepted for publication 4 July 2016
Published 7 September 2016 Volume 2016:6 Pages 23—31
Checked for plagiarism Yes
Review by Single-blind
Peer reviewers approved by Dr Akshita Wason
Peer reviewer comments 3
Editor who approved publication: Professor Francesco Chiappelli
Janet G Bauer,1 Sue S Spackman,2 Robert Fritz,2 Amanjyot K Bains,3 Jeanette Jetton-Rangel3
1Advanced Education Services, 2Division of General Dentistry, 3Center of Dental Research, Loma Linda University School of Dentistry, Loma Linda, CA, USA
Introduction: Best estimates of intervention outcomes are used when uncertainties in decision making are evidenced. Best estimates are often, out of necessity, from a context of less than quality evidence or needing more evidence to provide accuracy.
Purpose: The purpose of this article is to understand the best estimate behavior, so that clinicians and patients may have confidence in its quantification and validation.
Methods: To discover best estimates and quantify uncertainty, critical appraisals of the literature, gray literature and its resources, or both are accomplished. Best estimates of pairwise comparisons are calculated using meta-analytic methods; multiple comparisons use network meta-analysis. Manufacturers provide margins of performance of proprietary material(s). Lower margin performance thresholds or requirements (functional failure) of materials are determined by a distribution of tests to quantify performance or clinical competency. The same is done for the high margin performance thresholds (estimated true value of success) and clinician-derived critical values (material failure to function clinically). This quantification of margins and uncertainties assists clinicians in determining if reported best estimates are progressing toward true value as new knowledge is reported.
Analysis: The best estimate of outcomes focuses on evidence-centered care. In stochastic environments, we are not able to observe all events in all situations to know without uncertainty the best estimates of predictable outcomes. Point-in-time analyses of best estimates using quantification of margins and uncertainties do this.
Conclusion: While study design and methodology are variables known to validate the quality of evidence from which best estimates are acquired, missing are tolerance margins, or upper and lower performance requirements and clinician critical values, within which best estimates behave and are validated. Understanding the best estimate behavior toward true value may provide clinicians and patients confidence in decision making under uncertainty.
Keywords: metric, outcomes, quantification of margins and uncertainties, true value, performance margins
This work is published and licensed by Dove Medical Press Limited. The full terms of this license are available at https://www.dovepress.com/terms.php and incorporate the Creative Commons Attribution - Non Commercial (unported, v3.0) License. By accessing the work you hereby accept the Terms. Non-commercial uses of the work are permitted without any further permission from Dove Medical Press Limited, provided the work is properly attributed. For permission for commercial use of this work, please see paragraphs 4.2 and 5 of our Terms.Download Article [PDF] View Full Text [HTML][Machine readable]