Measuring inconsistency in meta-analyses
Reads0
Chats0
TLDR
A new quantity is developed, I 2, which the authors believe gives a better measure of the consistency between trials in a meta-analysis, which is susceptible to the number of trials included in the meta- analysis.Abstract:
Cochrane Reviews have recently started including the quantity I 2 to help readers assess the consistency of the results of studies in meta-analyses. What does this new quantity mean, and why is assessment of heterogeneity so important to clinical practice?
Systematic reviews and meta-analyses can provide convincing and reliable evidence relevant to many aspects of medicine and health care.1 Their value is especially clear when the results of the studies they include show clinically important effects of similar magnitude. However, the conclusions are less clear when the included studies have differing results. In an attempt to establish whether studies are consistent, reports of meta-analyses commonly present a statistical test of heterogeneity. The test seeks to determine whether there are genuine differences underlying the results of the studies (heterogeneity), or whether the variation in findings is compatible with chance alone (homogeneity). However, the test is susceptible to the number of trials included in the meta-analysis. We have developed a new quantity, I 2, which we believe gives a better measure of the consistency between trials in a meta-analysis.
Assessment of the consistency of effects across studies is an essential part of meta-analysis. Unless we know how consistent the results of studies are, we cannot determine the generalisability of the findings of the meta-analysis. Indeed, several hierarchical systems for grading evidence state that the results of studies must be consistent or homogeneous to obtain the highest grading.2–4
Tests for heterogeneity are commonly used to decide on methods for combining studies and for concluding consistency or inconsistency of findings.5 6 But what does the test achieve in practice, and how should the resulting P values be interpreted?
A test for heterogeneity examines the null hypothesis that all studies are evaluating the same effect. The usual test statistic …read more
Citations
More filters
Journal ArticleDOI
Cognitive motor interference while walking: a systematic review and meta-analysis
Emad Al-Yahya,Helen Dawes,Helen Dawes,Lesley Smith,Amanda Dennis,Kevin Howells,Janet Cockburn +6 more
TL;DR: It is suggested that cognitive tasks that involve internal interfering factors seem to disturb gait performance more than those involving external interfering factors and between the level of cognitive state and speed reduction under dual-task conditions.
Journal ArticleDOI
Cardiovascular sequelae of preeclampsia/eclampsia: a systematic review and meta-analyses.
TL;DR: Women with a history of preeclampsia/eClampsia have approximately double the risk of early cardiac, cerebrovascular, and peripheral arterial disease, and cardiovascular mortality and further research is needed to determine the mechanisms underlying these associations and to identify effective prevention strategies.
Journal ArticleDOI
Substance abuse and dependence in prisoners: a systematic review
TL;DR: The prevalence of substance abuse and dependence is typically many orders of magnitude higher in prisoners than the general population, particularly for women with drug problems, which highlights the need for screening for substance Abuse and dependence at reception into prison, effective treatment while in custody, and follow-up on release.
Journal ArticleDOI
Meta-regression in Stata
TL;DR: A revised version of the metareg command, which performs meta-analysis regression (meta-regression) on study-level summary data, is presented, which involves improvements to the estimation methods and the addition of an option to use a permutation test to estimate p-values.
Journal ArticleDOI
Thrombophilia in pregnancy: a systematic review
Lindsay Robertson,Olivia Wu,Peter Langhorne,Sara Twaddle,Peter Clark,Gordon D.O. Lowe,Isobel D. Walker,Mike Greaves,I. Brenkel,Lesley Regan,Ian A. Greer +10 more
TL;DR: It is confirmed that women with thrombophilia are at risk of developing venous thromboembolism and complications in pregnancy, however, despite the increase in relative risk, the absolute risk of VTE and adverse outcomes remains low.
References
More filters
Journal ArticleDOI
Quantifying heterogeneity in a meta‐analysis
TL;DR: It is concluded that H and I2, which can usually be calculated for published meta-analyses, are particularly useful summaries of the impact of heterogeneity, and one or both should be presented in publishedMeta-an analyses in preference to the test for heterogeneity.
Journal ArticleDOI
The combination of estimates from different experiments.
TL;DR: The problem of making a combined estimate has been discussed previously by Cochran and Yates and Cochran (1937) for agricultural experiments, and by Bliss (1952) for bioassays in different laboratories as discussed by the authors.
Journal ArticleDOI
Tamoxifen for early breast cancer: An overview of the randomised trials
TL;DR: The absolute improvement in recurrence was greater during the first 5 years, whereas the improvement in survival grew steadily larger throughout the first 10 years, and these benefits appeared to be largely irrespective of age, menopausal status, daily tamoxifen dose, and of whether chemotherapy had been given to both groups.
Journal Article
Tamoxifen for early breast cancer: an overview of the randomised trials. Early Breast Cancer Trialists' Collaborative Group
TL;DR: There have been many randomised trials of adjuvant tamoxifen among women with early breast cancer, and an updated overview of their results is presented in this paper, which approximately doubles the amount of evidence from trials of about 5 years of tamoxifier and, taking all trials together, on events occurring more than 5 years after randomisation.
Journal ArticleDOI
Funnel plots for detecting bias in meta-analysis: guidelines on choice of axis.
TL;DR: In this paper, the authors evaluated standard error, precision (inverse of standard error), variance, inverse of variance, sample size and log sample size (vertical axis) and log odds ratio, log risk ratio and risk difference (horizontal axis).