How (Not) to Use Risk Ratios in Sociological Research

Research output: Contribution to journalJournal articleResearchpeer-review

Documents

  • Full Text

    Final published version, 1.16 MB, PDF document

A small but growing literature uses the risk ratio as an association or effect measure. Unlike odds ratios, risk ratios are unaffected by rescaling or non-collapsibility bias and are straightforward to interpret. However, the risk ratio has one unattractive property that researchers need to be aware of: It is not symmetric with respect to the outcome definition. The ratio between two groups’ probability of success does not equal the inverse of the ratio between the two groups’ probability of failure. Choosing the category of a binary outcome to use as the “success” category can significantly affect substantive conclusions, particularly in research comparing risk ratios with highly different baserates of the “success” outcome. We give examples from discrimination and social mobility studies that illustrate this point, and we present rules of thumb for the use of the risk ratio depending on the baserate of the outcome.
Original languageEnglish
JournalSocius: Sociological Research for a Dynamic World
DOIs
Publication statusPublished - Sep 2023

    Research areas

  • Faculty of Social Sciences - risk ratio, association measure, effect measure, odd ratio, risk difference, quantitative methods

Number of downloads are based on statistics from Google Scholar and www.ku.dk


No data available

ID: 356951370