Issues in the selection of a summary statistic for meta‐analysis of clinical trials with binary outcomes

By J. Deeks. Statistics in Medicine, 2002

615 citations recorded by the source corpus.

Subfields: Economics and Econometrics, General Health Professions, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/a1e620688b7c0baa5d0f5f3ba50453f2e57fe43e

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

1. Georgia Salanti
2. Julian P. T. Higgins
3. Holger J. Schünemann
4. G. Guyatt
5. J. Brożek
6. A. Ades
7. N. Welton
8. S. Dias

In General Health Professions

1. Johannes B Reitsma
2. Georgia Salanti
3. A. Sutton
4. N. Welton
5. S. Dias
6. A. Ades
7. Karel G. M. Moons
8. Dan Jackson

In Statistics and Probability

1. Georgia Salanti
2. Julian P. T. Higgins
3. Ian R. White
4. Dan Jackson
5. A. Ades
6. N. Welton
7. A. Chaimani
8. S. Dias

Citations in the corpus

• Methods to estimate the between‐study variance and its uncertainty in meta‐analysis† (2015, methodology): “DerSimonian and Kacker (2007) compared the DL, HO, DL2, HO2, and PM methods (which we describe below) and showed that the DL2 estimator approximates the PM estimator, which may have some desirable statistical properties.”
• GetReal in network meta‐analysis: a review of the methodology (2016, background): “In principle, the choice of the summary statistic in any meta-analysis should be dictated (if possible) by biological justifications regarding the disease (Walter, 2000) and also by empirical evidence (Deeks, 2002).”
• Evidence Synthesis for Decision Making 2 (2013, methodology): “The logit model assumes additivity of effects on the logit scale.(36) Choice of scale can be guided by goodness of fit or by lower between-study heterogeneity, but there are seldom enough data to make this choice reliably, and logical considerations may play a larger role.”
• GRADE guidelines: 2. Framing the question and deciding on important outcomes. (2011, background): “a specific comparator is usually similar across a wide variety of baseline risks, it is usually appropriate for systematic reviews to generate single pooled estimates of relative effects across a wide range of patient subgroups [6,7,8].”
• Conceptual and Technical Challenges in Network Meta-analysis (2013, background): “Try to bypass Empirical evidence shows that some effect measures are associated with larger heterogeneity than others (30, 31).”
• The Effect of Suspect-Filler Similarity on Eyewitness Identification Decisions: A Meta-Analysis (2013, background): “However, odds ratio is also the least intuitive of the three measures (Deeks, 2002).”