Editing Meta-analysis (section)

===Validation of meta-analysis results===
The meta-analysis estimate represents a weighted average across studies and when there is [[study heterogeneity|heterogeneity]] this may result in the summary estimate not being representative of individual studies. Qualitative appraisal of the primary studies using established tools can uncover potential biases,<ref>{{cite journal | vauthors = Higgins JP, Altman DG, Gøtzsche PC, Jüni P, Moher D, Oxman AD, Savovic J, Schulz KF, Weeks L, Sterne JA | display-authors = 6 | title = The Cochrane Collaboration's tool for assessing risk of bias in randomised trials | journal = BMJ | volume = 343 | pages = d5928 | date = October 2011 | pmid = 22008217 | pmc = 3196245 | doi = 10.1136/bmj.d5928 }}</ref><ref>{{cite journal | vauthors = Whiting PF, Rutjes AW, Westwood ME, Mallett S, Deeks JJ, Reitsma JB, Leeflang MM, Sterne JA, Bossuyt PM | display-authors = 6 | title = QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies | journal = Annals of Internal Medicine | volume = 155 | issue = 8 | pages = 529–536 | date = October 2011 | pmid = 22007046 | doi = 10.7326/0003-4819-155-8-201110180-00009 | doi-access = free }}</ref> but does not quantify the aggregate effect of these biases on the summary estimate. Although the meta-analysis result could be compared with an independent prospective primary study, such external validation is often impractical. This has led to the development of methods that exploit a form of [[Cross-validation (statistics)|leave-one-out cross validation]], sometimes referred to as internal-external cross validation (IOCV).<ref>{{cite journal | vauthors = Royston P, Parmar MK, Sylvester R | title = Construction and validation of a prognostic model across several studies, with an application in superficial bladder cancer | journal = Statistics in Medicine | volume = 23 | issue = 6 | pages = 907–926 | date = March 2004 | pmid = 15027080 | doi = 10.1002/sim.1691 | s2cid = 23397142 }}</ref> Here each of the k included studies in turn is omitted and compared with the summary estimate derived from aggregating the remaining k- 1 studies.  A general '''validation statistic, Vn''' based on IOCV has been developed to measure the statistical validity of meta-analysis results.<ref>{{cite journal | vauthors = Willis BH, Riley RD | title = Measuring the statistical validity of summary meta-analysis and meta-regression results for use in clinical practice | journal = Statistics in Medicine | volume = 36 | issue = 21 | pages = 3283–3301 | date = September 2017 | pmid = 28620945 | pmc = 5575530 | doi = 10.1002/sim.7372 }}</ref> For test accuracy and prediction, particularly when there are multivariate effects, other approaches which seek to estimate the prediction error have also been proposed.<ref>{{cite journal | vauthors = Riley RD, Ahmed I, Debray TP, Willis BH, Noordzij JP, Higgins JP, Deeks JJ | title = Summarising and validating test accuracy results across multiple studies for use in clinical practice | journal = Statistics in Medicine | volume = 34 | issue = 13 | pages = 2081–2103 | date = June 2015 | pmid = 25800943 | pmc = 4973708 | doi = 10.1002/sim.6471 }}</ref>