Risk Of Bias In Non-Randomized Studies - of Interventions (ROBINS-I)

The ROBINS-I is a tool developed to assess the risk of bias from an individual non-randomized study that examines the effect of an intervention on an outcome.

ROBINS-I operates in the same manner as the RoB-2 and ROB-ME tools, whereby responses to signalling questions provide the basis for a judgement about the risk of bias in the specific synthesized result being assessed.

The tool and guidance on how to use it can be found here. 

A first draft of version 2 of the ROBINS-I tool is now available. Version 2 of the ROBINS-I implements changes that should make the tool more usable and risk of bias assessments more reliable. The tool now provides algorithms that suggest risk of bias judgment based on answers to signaling questions. It also addresses issues such as bias due to immortal time that were omitted from the 2016 version. 

Watch the webinar from October 2025, where Julian Higgins introduces the new ROBINS-I version 2 tool here.