Meta-analysis Spurious precision? Meta-analysis of observational studies

Egger, Matthias; Schneider, Martin; Smith, George Davey

doi:10.1136/bmj.316.7125.140

Cited by 883 publications

(600 citation statements)

References 42 publications

Supporting

Mentioning

579

Contrasting

Unclassified

Order By: Relevance

“…less than 3-to 4-fold 7,82,83 ) and do not relate to health outcomes that are rare in the types of patient studied. 4,6,7,9,[83][84][85] This limitation is not confined to the assessment of beneficial treatment effects, but applies equally to the detection of harmful effects. For, although unintended adverse effects may be more plausible than are any unintended beneficial effects, 86 the potential impact of the biases in observational studies is similar irrespective of the direction of the associations.…”

Section: Insert Panelmentioning

confidence: 99%

“…4,6,7,9,16,84 Confounding by indication, or contraindication, occurs when the treatment being considered tends to be provided more, or less, frequently to individuals with medical conditions or other characteristics that are associated with increased, or decreased, risks of various health outcomes (which is, of course, what would be expected to occur in clinical practice 105 ). Bias may also be introduced by other differences in the underlying risks of developing health outcomes among the individuals who have received a particular treatment and the individuals with whom they are compared who have not received that treatment.…”

Section: Biases Due To Differences In Underlying Risks Of Health Outcmentioning

confidence: 99%

See 1 more Smart Citation

Interpretation of the evidence for the efficacy and safety of statin therapy

et al. 2016

View full text Add to dashboard Cite

General rightsThis document is made available in accordance with publisher policies. Please cite only the published version using the reference above. Full terms of use are available: http://www.bristol.ac.uk/pure/about/ebr-terms SummaryThis review is intended to help clinicians, patients and the public make informed decisions about statin therapy for the prevention of heart attacks and strokes. It explains how the evidence that is available from randomized controlled trials yields reliable information about both the efficacy and safety of statin therapy. In addition, it discusses how claims that statins commonly cause adverse effects reflect a failure to recognise the limitations of other sources of evidence about the effects of treatment.Large-scale randomized trial evidence shows that statin therapy reduces the risk of heart attacks, ischaemic strokes and coronary revascularization procedures ("major vascular events") by about one quarter for each mmol/L reduction in low density lipoprotein (LDL) cholesterol during each year (after the first) that it continues to be taken. The absolute benefits of statin therapy depend on an individual's absolute risk of occlusive vascular events and the absolute reduction in LDL cholesterol that is achieved. For example, lowering LDL cholesterol by 2 mmol/L (77 mg/dL) with an effective low-cost statin regimen (e.g. atorvastatin 40 mg daily, costing about £2 per

show abstract

Section: Insert Panelmentioning

confidence: 99%

Section: Biases Due To Differences In Underlying Risks Of Health Outcmentioning

confidence: 99%

Interpretation of the evidence for the efficacy and safety of statin therapy

et al. 2016

View full text Add to dashboard Cite

show abstract

“…The main weakness of our paper is that of all meta-analyses: it is limited by the quality of the studies included. Because the studies were mainly observational in nature, the statistical combination of data might have been subject to selection and reporting biases (47). By establishing a strict methodology and a predefined review process, including a validity scale, we eliminated bias from our analysis where possible.…”

Section: Discussionmentioning

confidence: 99%

A Systematic Review and Meta-Analysis of Pregnancy Outcomes in Patients with Systemic Lupus Erythematosus and Lupus Nephritis

Smyth¹,

Oliveira²,

Lahr

et al. 2010

Clinical Journal of the American Society of Nephrology

544

437

View full text Add to dashboard Cite

Background and objectives: Studies of the impact of systemic lupus erythematosus (SLE) and its pregnancy complications have yielded conflicting results. Major limitations of these studies relate to their small numbers of patients and retrospective designs. The aim of this study was to perform a systematic literature review of pregnancy outcomes in women with SLE and a meta-analysis of the association of lupus nephritis with adverse pregnancy outcomes.Design, setting, participants, & measurements: We searched electronic databases from 1980 to 2009 and reviewed papers with validity criteria. Random-effects analytical methods were used to evaluate pregnancy complications rates.Results: Thirty-seven studies with 1842 patients and 2751 pregnancies were included. Maternal complications included lupus flare (25.6%), hypertension (16.3%), nephritis (16.1%), pre-eclampsia (7.6%), and eclampsia (0.8%). The induced abortion rate was 5.9%, and when excluded, fetal complications included spontaneous abortion (16.0%), stillbirth (3.6%), neonatal deaths (2.5%), and intrauterine growth retardation (12.7%). The unsuccessful pregnancy rate was 23.4%, and the premature birth rate was 39.4%. Meta-regression analysis showed statistically significant positive associations between premature birth rate and active nephritis and increased hypertension rates in subjects with active nephritis or a history of nephritis. History of nephritis was also associated with pre-eclampsia. Anti-phospholipid antibodies were associated with hypertension, premature birth, and an increased rate of induced abortion.Conclusions: In patients with SLE, both lupus nephritis and anti-phospholipid antibodies increase the risks for maternal hypertension and premature births. The presented evidence further supports timing of pregnancy relative to SLE activity and multispecialty care of these patients.

show abstract

“…This would require obtaining original continuous NA and SI data from the authors of previous studies, but for two reasons would be unsatisfactory solution and would only serve to obscure some obvious heterogeneity and bias in the contributing studies [38]. First, the validity of such a patient level meta-analysis assumes that all available data are included without substantial bias.…”

Section: Meta-analysis To the Rescue?mentioning

confidence: 99%

Are we witnessing the decline effect in the Type D personality literature? What can be learned?

Coyne¹,

Voogd²

2012

Journal of Psychosomatic Research

View full text Add to dashboard Cite

a b s t r a c t a r t i c l e i n f oAfter an unbroken series of positive, but underpowered studies seemed to demonstrate Type D personality predicting mortality in cardiovascular disease patients, initial claims now appear at least exaggerated and probably false. Larger studies with consistently null findings are accumulating. Conceptual, methodological, and statistical issues can be raised concerning the construction of Type D personality as a categorical variable, whether Type D is sufficiently distinct from other negative affect variables, and if it could be plausibly assumed to predict mortality independent of depressive symptoms and known biomedical factors, including disease severity. The existing literature concerning negative affect and health suggests a low likelihood of discovering a new negative affect variable that independently predicts mortality better than its many rivals. The apparent decline effect in the Type D literature is discussed in terms of the need to reduce the persistence of false positive findings in the psychosomatic medicine literature, even while preserving a context allowing risk-taking and discovery. Recommendations include greater transparency concerning research design and analytic strategy; insistence on replication with larger samples before accepting "discoveries" from small samples; reduced confirmatory bias; and availability of all relevant data. Such changes would take time to implement, face practical difficulties, and run counter to established practices. An interim solution is for readers to maintain a sense of pre-discovery probabilities, to be sensitized to the pervasiveness of the decline effect, and to be skeptical of claims based on findings reaching significance in small-scale studies that have not been independently replicated.© 2012 Elsevier Inc. All rights reserved. IntroductionMany "discoveries" turn out to be exaggerated or simply false across diverse research areas and disciplines. John Ioannidis [1] provoked concern with his demonstration that of the 49 most cited clinical research studies in major journals, replications of 34 had been attempted, and 41% of key findings had been refuted or shown to be substantially diminished. In a subsequent paper [2] he offered evidence that "most claimed research findings are false" and he and others [3-6] have since identified some mechanisms by which discoveries appear in the literature and then undergo a decline or refutation. Claims of breakthrough discoveries frequently arise in small positive studies that would seem to be too underpowered to detect an effect, and the inadequate sample size makes findings all the more attention grabbing.Yet, portrayals in the literature of such "discoveries" ignore the larger context of a strong confirmatory bias in published research papers, with unknown numbers of negative findings not being published and findings being declared discoveries simply because of having achieved an arbitrary level of significance. Moreover, statistically significant findings in small studies are nece...

show abstract

Meta-analysis Spurious precision? Meta-analysis of observational studies

Cited by 883 publications

References 42 publications

Interpretation of the evidence for the efficacy and safety of statin therapy

Interpretation of the evidence for the efficacy and safety of statin therapy

A Systematic Review and Meta-Analysis of Pregnancy Outcomes in Patients with Systemic Lupus Erythematosus and Lupus Nephritis

Are we witnessing the decline effect in the Type D personality literature? What can be learned?

Contact Info

Product

Resources

About