Concept Architecture
Concept
Theoretically, Odds Ratio (OR) is a comparative epidemiological measure that quantifies the strength of association between an exposure and an outcome by comparing the odds of the outcome occurring in one group with the odds in another. It is founded on probability theory and contingency table analysis and is the principal effect measure used in case-control studies and logistic regression. The concept exists to estimate relative associations when direct risk estimation is not possible or when modelling binary outcomes.
Mathematically, the Odds Ratio is represented as the ratio of two odds or, equivalently, as the cross-product ratio of a 2 ? 2 contingency table. It is a dimensionless measure in which an Odds Ratio greater than 1 indicates a positive association between exposure and outcome, an Odds Ratio less than 1 indicates a negative association, and an Odds Ratio equal to 1 indicates no association.
In practice, the Odds Ratio is estimated from contingency tables, case-control studies and logistic regression models. It is widely applied in epidemiology, clinical research and health economic evaluations to quantify exposure-outcome associations, estimate treatment effects for binary outcomes and synthesise evidence in meta-analyses.
Purpose
Used to quantify the association between an exposure and an outcome, estimate treatment or risk factor effects for binary outcomes, support epidemiological analyses and inform health economic decision-making.
Mathematical Formulae
Primary Formula
OR = (a ? d) / (b ? c)
where:
- a = exposed cases
- b = exposed non-cases
- c = unexposed cases
- d = unexposed non-cases
Supporting Formulae
Odds = P / (1 ? P)
OR = (Odds?) / (Odds?)
OR = exp(?)
95% CI = exp[ln(OR) � 1.96 ? SE(ln(OR))]
SE(ln(OR)) = �[(1/a) + (1/b) + (1/c) + (1/d)]
Related Mathematical Methods
- Logistic Regression
- Relative Risk
- Risk Ratio
- Hazard Ratio
- Likelihood Ratio
- Confidence Interval Estimation
- Mantel-Haenszel Method
- Meta-Analysis
Example
A case-control study investigates smoking and lung cancer.
| Lung Cancer | No Lung Cancer | |
|---|---|---|
| Smoker | 120 | 80 |
| Non-smoker | 60 | 140 |
Odds Ratio:
OR = (120 ? 140) / (80 ? 60)
OR = 16,800 / 4,800
OR = 3.50
Smokers have 3.5 times the odds of developing lung cancer compared with non-smokers.
Excel Implementation
| Function | Example Formula | Health Economics Application |
|---|---|---|
| Multiplication | =(B2*E2)/(C2*D2) | Calculates the Odds Ratio from a 2 ? 2 contingency table. |
| LN | =LN(F2) | Calculates the natural logarithm of the Odds Ratio for regression and meta-analysis. |
| EXP | =EXP(LN(F2)-1.96*G2) | Calculates the lower 95% confidence interval. |
| EXP | =EXP(LN(F2)+1.96*G2) | Calculates the upper 95% confidence interval. |
VBA (Optional)
A VBA macro can automatically calculate Odds Ratios, confidence intervals and contingency table summaries for multiple studies or patient subgroups.
Sources
- Rothman KJ, Greenland S, Lash TL. Modern Epidemiology. 4th ed.
- Hosmer DW, Lemeshow S, Sturdivant RX. Applied Logistic Regression. 3rd ed.
- Agresti A. Categorical Data Analysis. 3rd ed.
- Breslow NE, Day NE. Statistical Methods in Cancer Research. Volume I: The Analysis of Case-Control Studies.
- Drummond MF, et al. Methods for the Economic Evaluation of Health Care Programmes. 4th ed.
Related Concepts (2)
Library
Publications
1
Statistical Analysis of Cost-Effectiveness Data — Willan & Briggs, 1st Edition ed., 2006 (John Wiley & Sons)
A synthesis of statistical methods for analysing cost-effectiveness data, including net-benefit regression, confidence intervals for the ICER, cost-effectiveness acceptability curves, and covariate adjustment. Part of the Wiley Statistics in Practice series.
BookView source →
Frequently Asked Questions (6)
What is an odds ratio?
A measure comparing the odds of an outcome in one group to the odds in another, common in case-control studies and logistic regression.
Source: Cornfield 1951
Why is the odds ratio the natural measure in a case-control study?
An odds ratio compares the odds of an outcome in one group with the odds in another. It is the natural measure in a case-control study because such studies start by selecting people according to their outcome, cases and controls, which makes it impossible to calculate risks directly, whereas the odds of prior exposure can still be compared. The odds ratio also emerges directly from logistic regression. For rare outcomes it approximates the risk ratio, though for common ones it overstates the effect. Suiting outcome-based sampling is its strength. Rothman and colleagues (2008) describe this measure.
Source: Rothman et al. 2008
How is an odds ratio calculated?
An odds ratio is calculated as the ratio of the odds of the outcome in one group to the odds in another, where the odds in each group are the number with the outcome divided by the number without it. In a two-by-two table, it equals the cross-product ratio of the cell counts. In logistic regression, the exponentiated coefficient gives an odds ratio. So an odds ratio is calculated by comparing the odds of the outcome between groups, whether directly from counts or from a logistic model, giving a relative measure of association that can be estimated even in designs, such as case-control studies, where risks cannot be directly computed.
Source: Cornfield 1951
Why is the odds ratio used in case-control studies?
The odds ratio is used in case-control studies because such studies sample by outcome, selecting cases and controls, so the risk of the outcome cannot be estimated directly, but the odds ratio can, and it validly estimates the association between exposure and outcome under this design. It also approximates the risk ratio when the outcome is rare. So the odds ratio is used in case-control studies because it is the appropriate measure of association obtainable from their outcome-based sampling, providing a valid comparison of exposure between cases and controls, which is why it became the standard effect measure for this common study design.
Source: Cornfield 1951
How does an odds ratio differ from a risk ratio?
An odds ratio compares the odds of an outcome between groups, while a risk ratio compares the probabilities, or risks. The two are similar when the outcome is rare, but as the outcome becomes common the odds ratio grows more extreme than the risk ratio, moving further from one. The odds ratio can be estimated in case-control studies and logistic regression, where the risk ratio cannot. So the two differ in whether they compare odds or risks, and although often close for rare outcomes, they diverge for common ones, which means the odds ratio should not be interpreted as a risk ratio when the outcome is frequent.
Source: Rothman, Greenland & Lash 2008
What are the limitations of the odds ratio?
The limitations of the odds ratio include that it is harder to interpret intuitively than a risk ratio, and that it overstates the risk ratio when the outcome is common, so treating an odds ratio as a relative risk can be misleading for frequent outcomes. It also does not convey absolute risk. So the odds ratio is interpreted with care, particularly avoiding its misreading as a risk ratio when the outcome is not rare, and it is used alongside absolute measures, since, despite its usefulness in case-control studies and logistic regression, its interpretation is less direct and can mislead if its distinction from the risk ratio is ignored.
Source: Rothman, Greenland & Lash 2008
Trust Record
Verified by Dr Darrin Baines
British health economist
Professional identity: darrinbaines.org
Verification date: 9 Dec 2025
Content version: 1.0.0
Canonical Identity
- Persistent URI
- https://healtheconomics.wiki/concept/odds-ratio
- Term code
- HE-ES-RM-019
Stable URI · Machine-readable · Resolvable · CC BY 4.0