Get a Quote

Free Tools › ROBINS-I Tool

ROBINS-I Tool: Risk of Bias in Non-Randomised Studies of Interventions

Record ROBINS-I judgements across the seven bias domains for each non-randomised study, see the suggested overall risk of bias, and download traffic light and summary plots.

FreeNo account neededYour data stays in your browser

Domains and how to use them
  1. D1: Bias due to confoundingWhether factors that predict the outcome also influenced who received the intervention, and how well they were controlled.
  2. D2: Bias in selection of participants into the studyWhether selection into the study or the start of follow-up relates to both intervention and outcome.
  3. D3: Bias in classification of interventionsWhether intervention status was defined clearly and recorded without being affected by the outcome.
  4. D4: Bias due to deviations from intended interventionsDepartures from the intended intervention beyond usual practice, and how they were handled.
  5. D5: Bias due to missing dataMissing outcome, intervention or confounder data, and how it was handled.
  6. D6: Bias in measurement of outcomesComparable outcome assessment across groups and assessor awareness of the intervention.
  7. D7: Bias in selection of the reported resultWhether the result was selected from several outcomes, analyses or subgroups.

Answer the signalling questions in the official tool, then record your judgements here: ROBINS-I tool and guidance (riskofbias.info).

StudyD1D2D3D4D5D6D7Overall

Your entries are saved in this browser only. Nothing is uploaded.

Low if low in all domains; moderate if low or moderate in all; serious if serious in any (none critical); critical if critical in any. 'No information' is suggested when information is missing in a key domain and nothing is serious or critical; confirm it with your own judgement.

Summary plot

Traffic light plot

StudyD1D2D3D4D5D6D7OverallExample cohort 1−+++−++−Example cohort 2×−+−+−+×Example cohort 3−+−+?+−?Example cohort 4!×+−−×+!D1: Bias due to confoundingD2: Bias in selection of participants into the studyD3: Bias in classification of interventionsD4: Bias due to deviations from intended interventionsD5: Bias due to missing dataD6: Bias in measurement of outcomesD7: Bias in selection of the reported result+Low−Moderate×Serious!Critical?No information

Summary plot

D1. Bias due to confounding50%25%25%D2. Bias in selection of participants into the study50%25%25%D3. Bias in classification of interventions75%25%D4. Bias due to deviations from intended interventions50%50%D5. Bias due to missing data25%50%25%D6. Bias in measurement of outcomes50%25%25%D7. Bias in selection of the reported result75%25%Overall25%25%25%25%0%25%50%75%100%LowModerateSeriousCriticalNo information
Get new free research tools firstOccasional emails when we add tools and guides. No spam.

We only use your email to send these updates, never share it, and you can unsubscribe by replying to any email or writing to info@timelyscholar.com. Privacy Policy

How to Use the ROBINS-I Tool

  1. 1

    Answer the official signalling questions

    Use the linked tool document for each study or result.

  2. 2

    Record your judgements

    One row per study, one column per domain; the overall judgement is suggested for you.

  3. 3

    Download the figures

    Traffic light and summary plots as PNG or SVG, plus a CSV of your table.

What is ROBINS-I?

ROBINS-I assesses risk of bias in the results of non-randomised studies that compare the effects of interventions, such as cohort studies. It judges each study against a hypothetical target trial.

It has seven domains: confounding, selection of participants, classification of interventions, deviations from intended interventions, missing data, measurement of outcomes and selection of the reported result. Judgements are low, moderate, serious or critical risk, or no information.

A low risk of bias means the study is comparable to a well-performed randomised trial in that domain, which is rare for confounding.

The tool here follows the 2016 version used in the Cochrane Handbook. A draft ROBINS-I Version 2 was released in November 2025 and may still change.

How it is calculated

Sources

ROBINS-I Tool: FAQ

What is the difference between ROBINS-I and ROBINS-E?

ROBINS-I is for studies of interventions (things people choose or are given). ROBINS-E is for studies of exposures, such as environmental or occupational exposures.

Should I use ROBINS-I Version 2?

Version 2 was still a draft when this page was written. Use the version your protocol specifies and cite it.

Related Free Tools

RoB 2 Tool (Risk of Bias 2)ROBINS-E ToolNewcastle-Ottawa Scale CalculatorAll free tools →
Get a Free Quote