Individual participant data meta-analyses should not ignore clustering
| dc.contributor.author | Guo, Boliang | |
| dc.date.accessioned | 2018-03-15T13:51:35Z | |
| dc.date.available | 2018-03-15T13:51:35Z | |
| dc.date.issued | 2013 | |
| dc.identifier.citation | Abo-Zaid, G., Guo, B., Deeks, J. J., Riley, R. D., Debray, T. P. A., Moons, K. G. M. & Steyerberg, E. W. (2013). Individual participant data meta-analyses should not ignore clustering. Journal of Clinical Epidemiology, 66 (8), pp.865-873. | en |
| dc.identifier.other | 10.1016/j.jclinepi.2012.12.017 | |
| dc.identifier.uri | http://hdl.handle.net/20.500.12904/11784 | |
| dc.description | © 2013 Elsevier Inc. Published by Elsevier Inc. | |
| dc.description.abstract | Objectives: Individual participant data (IPD) meta-analyses often analyze their IPD as if coming from a single study. We compare this approach with analyses that rather account for clustering of patients within studies. Study Design and Setting: Comparison of effect estimates from logistic regression models in real and simulated examples. Results: The estimated prognostic effect of age in patients with traumatic brain injury is similar, regardless of whether clustering is accounted for. However, a family history of thrombophilia is found to be a diagnostic marker of deep vein thrombosis [odds ratio, 1.30; 95% confidence interval (CI): 1.00, 1.70; P = 0.05] when clustering is accounted for but not when it is ignored (odds ratio, 1.06; 95% CI: 0.83, 1.37; P = 0.64). Similarly, the treatment effect of nicotine gum on smoking cessation is severely attenuated when clustering is ignored (odds ratio, 1.40; 95% CI: 1.02, 1.92) rather than accounted for (odds ratio, 1.80; 95% CI: 1.29, 2.52). Simulations show models accounting for clustering perform consistently well, but downwardly biased effect estimates and low coverage can occur when ignoring clustering. Conclusion: Researchers must routinely account for clustering in IPD meta-analyses; otherwise, misleading effect estimates and conclusions may arise. © 2013 Elsevier Inc. All rights reserved. | |
| dc.description.uri | http://www.jclinepi.com/article/S0895-4356(13)00072-3/fulltext | |
| dc.format | Full text uploaded | |
| dc.subject | Cardiovascular diseases | en |
| dc.subject | Data collection | en |
| dc.subject | Statistics | en |
| dc.subject | Thrombosis | en |
| dc.subject | Smoking cessation | en |
| dc.subject | Brain injuries | en |
| dc.title | Individual participant data meta-analyses should not ignore clustering | en |
| dc.type | Article | |
| refterms.dateFOA | 2021-11-30T13:43:14Z | |
| html.description.abstract | Objectives: Individual participant data (IPD) meta-analyses often analyze their IPD as if coming from a single study. We compare this approach with analyses that rather account for clustering of patients within studies. Study Design and Setting: Comparison of effect estimates from logistic regression models in real and simulated examples. Results: The estimated prognostic effect of age in patients with traumatic brain injury is similar, regardless of whether clustering is accounted for. However, a family history of thrombophilia is found to be a diagnostic marker of deep vein thrombosis [odds ratio, 1.30; 95% confidence interval (CI): 1.00, 1.70; P = 0.05] when clustering is accounted for but not when it is ignored (odds ratio, 1.06; 95% CI: 0.83, 1.37; P = 0.64). Similarly, the treatment effect of nicotine gum on smoking cessation is severely attenuated when clustering is ignored (odds ratio, 1.40; 95% CI: 1.02, 1.92) rather than accounted for (odds ratio, 1.80; 95% CI: 1.29, 2.52). Simulations show models accounting for clustering perform consistently well, but downwardly biased effect estimates and low coverage can occur when ignoring clustering. Conclusion: Researchers must routinely account for clustering in IPD meta-analyses; otherwise, misleading effect estimates and conclusions may arise. © 2013 Elsevier Inc. All rights reserved. |
