|
Comparison of IPD and APD Meta-Analyses |
|||
| Steps in Meta-Analysis |
IPD |
APD |
|
|
|
|||
| Explicit and Relevant Clinical Question |
√ |
√ |
|
| Exhaustive Search |
All published studies |
√ |
√ |
| All presented studies |
√ |
√ |
|
| All completed studies |
√ |
± |
|
| Screening: inclusion/exclusion criteria |
√ |
√ |
|
| Data Acquisition (extraction/transfer) |
Aggregate data |
√ |
√ |
| Individual patient data |
√ |
- |
|
| Data Checking |
Source data |
± |
- |
| Submitted data |
√ |
√ |
|
| Published/presented |
√ |
√ |
|
| Data Updating |
√ |
± |
|
| Missing Studies/Data |
± |
± |
|
| Uniform outcomes |
√ |
- |
|
| Tests for heterogeneity |
√ |
√ |
|
| Estimating Summary Effect Measures |
Binomial data |
√ |
√ |
| Time-to-event data |
√ |
± |
|
| Exploring Heterogeneity Subgroup analyses |
Study Level |
√ |
√ |
| Patient Level |
√ |
- |
|
Lyman and Kuderer BMC Medical Research Methodology 2005 5:14 doi:10.1186/1471-2288-5-14 |
|||