Multivariate meta analysis with potentially correlated marketing study results

Sohn, So Young

doi:10.1002/1520-6750(200009)47:6<500::aid-nav3>3.0.co;2-z

Cited by 20 publications

(23 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our simulation results highlight that a normal model for BRMA is preferable to two separate URMAs for estimating the pooled endpoints, and our results are consistent with previous findings that show how the inclusion of correlation allows the 'borrowing of strength' across endpoints [1,10,19]. We thus recommend practitioners use a BRMA rather than two separate URMAs where possible.…”

Section: Discussionsupporting

confidence: 89%

See 1 more Smart Citation

Bivariate random-effects meta-analysis and the estimation of between-study correlation

Riley

Abrams

Sutton

et al. 2007

BMC Med Res Methodol

202

243

View full text Add to dashboard Cite

show abstract

Section: Discussionsupporting

confidence: 89%

“…The sizes of the meta-analysis were either n = 5 or n = 50 studies for complete data, and either n = 10 or n = 50 for missing data. Our method of simulation was deliberately chosen to be similar to that previously used by Berkey et al [1] and Sohn [19]. As an example, we now describe the simulation procedure for scenario (i) with n = 50 .…”

Section: Methodsmentioning

confidence: 99%

Bivariate random-effects meta-analysis and the estimation of between-study correlation

Riley

Abrams

Sutton

et al. 2007

BMC Med Res Methodol

202

243

View full text Add to dashboard Cite

show abstract

“…In such situations V i → D i and we would not expect the within‐study correlations to have much effect, as ultimately borne out in the simulation results of Ishak et al (2008). Sohn (2000) has also shown that even the within‐study variances and have little influence in such situations. The question thus remains regarding the exact influence of the within‐study correlation on the pooled estimates in other situations, e.g.…”

Section: Analytic Assessment Of the Effect Of Within‐study Correlamentioning

confidence: 99%

Multivariate Meta-Analysis: The Effect of Ignoring Within-Study Correlation

Riley

2009

Journal of the Royal Statistical Society Series A: Statistics in Society

187

282

View full text Add to dashboard Cite

Multivariate meta-analysis allows the joint synthesis of summary estimates from multiple end points and accounts for their within-study and between-study correlation. Yet practitioners usually meta-analyse each end point independently. I examine the role of within-study correlation in multivariate meta-analysis, to elicit the consequences of ignoring it. Using analytic reasoning and a simulation study, the within-study correlation is shown to influence the 'borrowing of strength' across end points, and wrongly ignoring it gives meta-analysis results with generally inferior statistical properties; for example, on average it increases the mean-square error and standard error of pooled estimates, and for non-ignorable missing data it increases their bias. The influence of within-study correlation is only negligible when the within-study variation is small relative to the between-study variation, or when very small differences exist across studies in the within-study covariance matrices. The findings are demonstrated by applied examples within medicine, dentistry and education. Meta-analysts are thus encouraged to account for the correlation between end points. To facilitate this, I conclude by reviewing options for multivariate meta-analysis when within-study correlations are unknown; these include obtaining individual patient data, using external information, performing sensitivity analyses and using alternatively parameterized models. Copyright (c) 2009 Royal Statistical Society.

show abstract

“…In this study, we have also not explored whether our multivariate models would improve our point estimates in the presence of missing data since our example data set had very minimal missing data. In the literature, some studies have shown that, in the presence of large amount of missing data, the ‘borrowing of strength’ from other studies in a multivariate meta-analysis can give more precise estimates compared to the univariate meta-analysis [39], [48], [49]. This has also been shown in a particular case of outcome reporting bias, where the impact of this bias on the precision of point estimates was reduced in the multivariate meta-analysis compared to univariate meta-analysis [38].…”

Section: Discussionmentioning

confidence: 99%

Meta-Analysis of Effect Sizes Reported at Multiple Time Points Using General Linear Mixed Model

et al. 2016

View full text Add to dashboard Cite

Meta-analysis of longitudinal studies combines effect sizes measured at pre-determined time points. The most common approach involves performing separate univariate meta-analyses at individual time points. This simplistic approach ignores dependence between longitudinal effect sizes, which might result in less precise parameter estimates. In this paper, we show how to conduct a meta-analysis of longitudinal effect sizes where we contrast different covariance structures for dependence between effect sizes, both within and between studies. We propose new combinations of covariance structures for the dependence between effect size and utilize a practical example involving meta-analysis of 17 trials comparing postoperative treatments for a type of cancer, where survival is measured at 6, 12, 18 and 24 months post randomization. Although the results from this particular data set show the benefit of accounting for within-study serial correlation between effect sizes, simulations are required to confirm these results.

show abstract

Multivariate meta analysis with potentially correlated marketing study results

Cited by 20 publications

References 27 publications

Bivariate random-effects meta-analysis and the estimation of between-study correlation

Bivariate random-effects meta-analysis and the estimation of between-study correlation

Multivariate Meta-Analysis: The Effect of Ignoring Within-Study Correlation

Meta-Analysis of Effect Sizes Reported at Multiple Time Points Using General Linear Mixed Model

Contact Info

Product

Resources

About