Influence of Reported Study Design Characteristics on Intervention Effect Estimates From Randomized, Controlled Trials

By J. Savović, Hayley E. Jones, Douglas G. Altman, Ross J. Harris, Peter Jüni, J. Pildal, B. Als-Nielsen, E. Balk, C. Gluud, L. Gluud and 8 more. Annals of Internal Medicine, 2012

1,002 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/5667b851bbf788508a249be0a5243029fcf25bdd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Statistics and Probability

Citations in the corpus

CONSORT 2025 statement: updated guideline for reporting randomised trials. (2025, positive): “4 Similarly, having a clear and transparent trial protocol is important because it prespecifies the methods used in the trial, such as the primary outcome, thereby reducing the likelihood of undeclared post hoc changes.”
CONSORT 2025 statement: updated guideline for reporting randomised trials (2025, neutral): ““Readers should not have to infer what was probably done; they should be told explicitly.””
Transcatheter Versus Surgical Aortic Valve Replacement in Patients With Severe Aortic Valve Stenosis: 1-Year Results From the All-Comers NOTION Randomized Clinical Trial. (2015, methodology): “Several outcomes were assessed unblinded as to procedure; accordingly, assessments of all outcomes apart from death could be subject to bias (29,30).”
Empirically Supported Treatment: Recommendations for a New Model (2015, background): “…generally, design weaknesses related to allocation concealment, blinding, and randomization methods may be expected to inﬂu-ence effect estimates, particularly when outcomes are subjective (Savovic et al., 2012), which is the case in most trials of psychological treatments (Wood et al., 2008).”
Thresholds for statistical and clinical significance in systematic reviews with meta-analytic methods (2014, background): “The bias risk domains generation of allocation sequence, allocation concealment, blinding of participants and treatment providers, blinding of outcome assessors, incomplete outcome data (see paragraph below), selective outcome reporting, and industry funding have been shown to be of particular impor”
Burden of disease from inadequate water, sanitation and hygiene in low- and middle-income settings: a retrospective analysis of data from 145 countries (2014, background): “When correcting for bias due to non-blinding in studies using subjective health outcomes (Savovi c et al. 2012), this estimate changes to 0.77 (95% CI 0.32–1.86) and becomes non-significant.”
Is network meta-analysis as valid as standard pairwise meta-analysis? It all depends on the distribution of effect modifiers (2013, background): “By doing so, the difference in observed outcomes in randomized trials, defined as the treatment effect (or effect size), can be attributed to differences in interventions compared (assuming that there are no other systematic differences resulting in bias, such as issues in concealment of treatment a”
Burden of disease from inadequate water, sanitation and hygiene for selected adverse health outcomes: An updated analysis with a focus on low- and middle-income countries (2019, methodology): “Exposure-response relationships linking point-of-use drinking water or hygiene interventions and diarrhoea were therefore bias-adjusted based on empirical evidence (Savović et al., 2012)(Tables S1 and S2 in the Supplementary File 1) using a previously published method (Wolf et al.”