About this example
ROBINS-I rates non-randomised studies of interventions against a hypothetical target trial, on a four-level scale from low to critical risk of bias. Confounding is usually the domain that decides the overall judgement, and this example shows the typical pattern: a column of moderate, serious and one critical judgement in D1.
“No information” gets its own blue symbol, so readers can tell missing reporting from an assessed risk. A study at critical risk in any domain is at critical risk overall, and most reviews leave such studies out of the synthesis.
The data
| Study | Confounding | Selection | Classification | Deviations | Missing data | Measurement | Reporting | Overall |
|---|---|---|---|---|---|---|---|---|
| Johansson 2012 | Serious | Low | Low | Low | Moderate | Low | Moderate | Serious |
| Kato 2014 | Moderate | Low | Low | Low | Low | Moderate | Low | Moderate |
| Larsen 2015 | Critical | Moderate | Low | Moderate | Serious | Low | Moderate | Critical |
| Moreau 2016 | Moderate | Low | Low | Low | Low | Low | Low | Moderate |
| Nakamura 2017 | Serious | Low | Moderate | Low | Moderate | Moderate | Low | Serious |
| Okafor 2019 | Moderate | Moderate | Low | No information | Low | Low | Moderate | Moderate |
| Petersen 2020 | Serious | Low | Low | Low | No information | Moderate | Low | Serious |
| Quinn 2021 | Moderate | Low | Low | Low | Low | Low | Low | Moderate |
Open the example, replace the data with your own, and export the figure as SVG, PDF, PNG or TIFF.