Library of risk of bias tools


Study design(s) targeted by the tool Cohort studiescohort-study Non-randomised studies of interventionsnrsi
Additional details on designs Comparative follow-up studies of the effects of interventions; modifications are in process for other designs. These will be added as they become available.
Tool area Health
Link to the tool Get the ROBINS-I tool (Google doc)


Primary publication Sterne JA, Hernan MA, Reeves BC, Savovic J, Berkman ND, Viswanathan M, et al. ROBINS-I: a tool for assessing risk of bias in non-randomised studies of interventions. BMJ 2016;355
DOI 10.1136/bmj.i4919
Guidance document Get the ROBINS-I guidance (Google doc)

None known – please contact us if you are aware of any training that should be listed here

Language English

None known – please contact us if you are aware of any translations that should be listed here.

Record last updated 24/08/2023

Related tools and Publications

Previous versions


Updated versions


Related tools



Jeyaraman MM, Robson RC, Copstein L, Al-Yousif N, Pollock M, Xia J, et al. Customized guidance/training improved the psychometric properties of methodologically rigorous risk of bias instruments for non-randomized studies. J Clin Epidemiol. 2021;136:157-67.

Zhang Y, Huang L, Wang D, Ren P, Hong Q, Kang D. The ROBINS-I and the NOS had similar reliability but differed in applicability: A random sampling observational studies of systematic reviews/meta-analysis. J Evid Based Med. 2021;14(2):112-22.

Minozzi S, Cinquini M, Gianola S, Castellini G, Gerardi C, Banzi R. Risk of bias in nonrandomized studies of interventions showed low inter-rater reliability and challenges in its application. J Clin Epidemiol. 2019;112:28-35.

Losilla JM, Oliveras I, Marin-Garcia JA, Vives J. Three risk of bias tools lead to opposite conclusions in observational research synthesis. J Clin Epidemiol. 2018;101:61-72.

Other publications

The Cochrane handbook contains some guidance on how to asssess other non-randomized designs including uncontrolled before-after studies including interrupted time-series and controlled before after-studies.


Key Criteria

Focuses on risk of bias, or makes a distinction between items that assess risk of bias and other aspects of study quality Yes
Offers a method to reach either a domain specific or overall assessment of risk of bias Yes
Tool development involving a range of stakeholders from different disciplines (e.g. methodologists, statisticians, clinicians) Yes
Avoids recommending use of summary numerical quality scores Yes