Ronny Gunnarsson. "Relative risk / Odds ratio" [on INFOVOICE.SE]. Available on: https://infovoice.se/relative-risk-odds-ratio/. Information was retrieved November 9, 2024.
Suggested pre-reading | What this web page adds |
---|---|
This web-page provides an introduction to Relative risk / odds ratio. Reading this will give you an understanding of these concepts and how to use them. |
(Denna webbsida är under konstruktion. Vi beklagar olägenheten.)
Odds ratio (OR) and relative risk ratio (RR) are typically measures of an association between two binary variables. However, odds ratio can also denote the increased odds for a specified change in an independent variable (read more about this on the page for logistic regression).
In a cohort study an exposure may be associated with a later increased or decreased risk for a specific disease. In this case these associations are often labelled “risk odds ratio (ROR)” and “risk ratio (RR)”.
In cross-sectional studies where the prevalence of one binary variable is associated with the simultaneous prevalence of another binary variable the same measures are often labelled “prevalence odds ratio (POR)” and “prevalence ratio (PR)” (the latter is sometimes also referred to as “prevalence rate ratio”).
OR and ROR are mathematically the same. Similarly, the RR and PR are mathematically the same.
Relative risk is often considered a better estimate of association, at least when the prevalence of any of the variables is above 10% . However, odds ratio is most often uses since most statistical software delivers odds ratios when doing logistic regression.
Useful links
References
Ronny Gunnarsson. "Relative risk / Odds ratio" [on INFOVOICE.SE]. Available on: https://infovoice.se/relative-risk-odds-ratio/. Information was retrieved November 9, 2024.