A large-scale assessment of temporal trends in meta-analyses using systematic review reports from the Cochrane Library
Introduction: Previous studies suggest many systematic reviews contain meta-analyses that display temporal trends, such as the first study’s result being more extreme than later studies’, or a drift in the pooled estimate. We assessed the extent and characteristics of temporal trends using all Cochr...
| Asıl Yazarlar: | , , |
|---|---|
| Materyal Türü: | Journal article |
| Baskı/Yayın Bilgisi: |
John Wiley & Sons Ltd
2017
|
| _version_ | 1826296424867823616 |
|---|---|
| author | Fanshawe, T Shaw, L Spence, G |
| author_facet | Fanshawe, T Shaw, L Spence, G |
| author_sort | Fanshawe, T |
| collection | OXFORD |
| description | Introduction: Previous studies suggest many systematic reviews contain meta-analyses that display temporal trends, such as the first study’s result being more extreme than later studies’, or a drift in the pooled estimate. We assessed the extent and characteristics of temporal trends using all Cochrane intervention reports published 2008-2012. <br/><br/> Methods: We selected the largest meta-analysis within each report and analysed trends using methods including a Z-test (first versus subsequent estimates); generalised least squares (GLS); and CUSUM charts. Predictors considered include meta-analysis size and review group. <br/><br/> Results: Of 1,288 meta-analyses containing at least four studies, the point estimate from the first study was more extreme and in the same direction as the pooled estimate in 738 (57%), with a statistically significant difference (first versus subsequent) in 165 (13%). GLS indicated trends in 717 (56%); 18% of fixed-effects analyses had at least one violation of CUSUM limits. For some methods, meta-analysis size was associated with temporal patterns and use of a random-effects model, but there was no consistent association with review group. <br/><br/> Conclusions: All results suggest more meta-analyses demonstrate temporal patterns than would be expected by chance. Hence, assuming the standard meta-analysis model without temporal trend is sometimes inappropriate. Factors associated with trends are likely to be context-specific. |
| first_indexed | 2024-03-07T04:16:08Z |
| format | Journal article |
| id | oxford-uuid:c97cd33b-dba9-4ce5-b208-8de55aca3fce |
| institution | University of Oxford |
| last_indexed | 2024-03-07T04:16:08Z |
| publishDate | 2017 |
| publisher | John Wiley & Sons Ltd |
| record_format | dspace |
| spelling | oxford-uuid:c97cd33b-dba9-4ce5-b208-8de55aca3fce2022-03-27T06:59:23ZA large-scale assessment of temporal trends in meta-analyses using systematic review reports from the Cochrane LibraryJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:c97cd33b-dba9-4ce5-b208-8de55aca3fceSymplectic Elements at OxfordJohn Wiley & Sons Ltd2017Fanshawe, TShaw, LSpence, GIntroduction: Previous studies suggest many systematic reviews contain meta-analyses that display temporal trends, such as the first study’s result being more extreme than later studies’, or a drift in the pooled estimate. We assessed the extent and characteristics of temporal trends using all Cochrane intervention reports published 2008-2012. <br/><br/> Methods: We selected the largest meta-analysis within each report and analysed trends using methods including a Z-test (first versus subsequent estimates); generalised least squares (GLS); and CUSUM charts. Predictors considered include meta-analysis size and review group. <br/><br/> Results: Of 1,288 meta-analyses containing at least four studies, the point estimate from the first study was more extreme and in the same direction as the pooled estimate in 738 (57%), with a statistically significant difference (first versus subsequent) in 165 (13%). GLS indicated trends in 717 (56%); 18% of fixed-effects analyses had at least one violation of CUSUM limits. For some methods, meta-analysis size was associated with temporal patterns and use of a random-effects model, but there was no consistent association with review group. <br/><br/> Conclusions: All results suggest more meta-analyses demonstrate temporal patterns than would be expected by chance. Hence, assuming the standard meta-analysis model without temporal trend is sometimes inappropriate. Factors associated with trends are likely to be context-specific. |
| spellingShingle | Fanshawe, T Shaw, L Spence, G A large-scale assessment of temporal trends in meta-analyses using systematic review reports from the Cochrane Library |
| title | A large-scale assessment of temporal trends in meta-analyses using systematic review reports from the Cochrane Library |
| title_full | A large-scale assessment of temporal trends in meta-analyses using systematic review reports from the Cochrane Library |
| title_fullStr | A large-scale assessment of temporal trends in meta-analyses using systematic review reports from the Cochrane Library |
| title_full_unstemmed | A large-scale assessment of temporal trends in meta-analyses using systematic review reports from the Cochrane Library |
| title_short | A large-scale assessment of temporal trends in meta-analyses using systematic review reports from the Cochrane Library |
| title_sort | large scale assessment of temporal trends in meta analyses using systematic review reports from the cochrane library |
| work_keys_str_mv | AT fanshawet alargescaleassessmentoftemporaltrendsinmetaanalysesusingsystematicreviewreportsfromthecochranelibrary AT shawl alargescaleassessmentoftemporaltrendsinmetaanalysesusingsystematicreviewreportsfromthecochranelibrary AT spenceg alargescaleassessmentoftemporaltrendsinmetaanalysesusingsystematicreviewreportsfromthecochranelibrary AT fanshawet largescaleassessmentoftemporaltrendsinmetaanalysesusingsystematicreviewreportsfromthecochranelibrary AT shawl largescaleassessmentoftemporaltrendsinmetaanalysesusingsystematicreviewreportsfromthecochranelibrary AT spenceg largescaleassessmentoftemporaltrendsinmetaanalysesusingsystematicreviewreportsfromthecochranelibrary |