Written and maintained by CASRAI Editorial Board
Published · Last updated
On this page
An odds ratio (OR) of 2.0 does not mean “twice as likely” — it means the odds of the outcome are twice as large, and odds are not the same thing as probability (risk). This distinction sounds pedantic until you see how far the two diverge numerically: for a common outcome, an OR of 3.5 can correspond to a real risk ratio of only 2.0. Reporting “3.5 times more likely” when the true risk increase is 2-fold is not a rounding error — it is a different, larger claim than the data support. This guide gives the correct interpretation language, works a numeric example that shows exactly where OR and RR pull apart, and covers the below-1 direction confusion and the adjusted-versus-crude reading that trip up even careful readers of a regression table.
Short answer: an odds ratio compares the odds of an outcome in two groups. An OR of 1 means no association, above 1 means higher odds in the exposed group, and below 1 means lower odds. Read it as “times the odds,” never “times as likely,” unless the outcome is rare. Always report the 95% confidence interval and the reference group.
A Worked Example First
Suppose a study compares a complication rate between two treatment groups, 100 patients each:
| Complication | No complication | Total | |
|---|---|---|---|
| Treatment A | 60 | 40 | 100 |
| Treatment B | 30 | 70 | 100 |
Two different summary numbers can be computed from this same table, and they answer two different questions:
- Risk (probability) of complication: Group A = 60/100 = 0.60; Group B = 30/100 = 0.30. Risk ratio = 0.60 / 0.30 = 2.0 — Group A patients were twice as likely to have a complication.
- Odds of complication: Group A = 60/40 = 1.5; Group B = 30/70 ≈ 0.4286. Odds ratio = 1.5 / 0.4286 ≈ 3.5 — Group A’s odds of complication were 3.5 times Group B’s odds.
Both numbers are correct descriptions of the same data. The sentence “patients in Group A were 3.5 times more likely to have a complication” is not one of them — that sentence describes the risk ratio, and the actual risk ratio here is 2.0. The OR of 3.5 overstates the true risk increase by 75% when read as if it were a risk ratio. This is exactly why the wrong-phrasing trap matters: “X times more likely” is risk-ratio language, and substituting an odds ratio into it silently inflates whatever effect you’re describing.
Odds Are Not Probability — The Language That Stays Correct
Odds and probability are related but not interchangeable: odds = p / (1 − p), where p is the probability of the outcome. At low probabilities (a rare outcome), odds and probability are numerically close, which is why the confusion so often goes unnoticed — and why it becomes dangerous exactly when the outcome is common, as in the worked example above. The language that stays accurate for an odds ratio:
- Correct: “The odds of the outcome were 2.0 times higher in Group A” or “Group A had twice the odds of the outcome.”
- Correct: “The odds ratio was 2.0 (95% CI, x–y).”
- Incorrect: “Group A patients were 2.0 times more likely to have the outcome” — “more likely” is probability language, and it is only a valid restatement of an odds ratio when the outcome is rare (conventionally under about 10% in both groups). Outside that range, say “odds,” not “likely” or “risk.”
This is the same reason a hazard ratio cannot be read as “more likely” either — both are ratios of a different underlying quantity (a rate, or odds) being casually substituted for a ratio of risk. The fix in both cases is the same: name the quantity the ratio is actually a ratio of.
When an Odds Ratio Does Approximate a Risk Ratio
The “rare disease assumption” is the specific, named condition under which reading an OR as if it were an RR is defensible as an approximation rather than an error. When the outcome’s probability is low in both compared groups (commonly cited as roughly under 10%), (1 − p) in the odds formula is close to 1 for both groups, so odds ≈ probability and OR ≈ RR. This is also the reason case-control studies report an odds ratio rather than a risk ratio in the first place: a case-control design fixes the ratio of cases to controls by the researcher’s sampling choice rather than by true population prevalence, so a valid risk ratio cannot be calculated directly from the sample at all — odds ratio is the only measure of association case-control data can legitimately produce, and under the rare-disease assumption it closely approximates the risk ratio a cohort study of the same exposure would have shown. See CASRAI’s case-control vs. cohort study comparison for the full design distinction. Cohort and randomized-trial designs, by contrast, can report either measure directly — and when the outcome is common, as in the worked example above, they diverge exactly as shown, which is why choosing (and correctly labeling) the right one matters.
The Below-1 Direction Confusion
An OR below 1.0 indicates lower odds of the outcome in the group being compared to the reference group — a protective or negative association, not “no effect.” The confusion that trips up readers here runs two directions:
- Misreading the magnitude. An OR of 0.5 means the odds are half those of the reference group — it does not mean “50% lower risk.” Converting an OR below 1 to a percentage change in odds is (1 − OR) × 100, e.g., OR = 0.68 → a 32% reduction in odds, not in probability of the outcome.
- Misreading the reference direction. Which group is “higher odds” and which is “lower odds” depends entirely on which category was coded as the reference level in the model. An OR of 0.5 for “Group A vs. Group B” is the same underlying association as an OR of 2.0 for “Group B vs. Group A” — always check the stated reference category before interpreting the direction, and always state it explicitly when reporting your own results.
The confidence interval is what determines whether a below-1 (or above-1) OR is distinguishable from no association at all: if the 95% CI spans 1.0, the data are consistent with no difference in odds between groups, regardless of how far the point estimate itself sits from 1.0.
Adjusted vs. Crude: Reading an Odds Ratio in a Regression Table
A regression results table commonly reports two odds ratios for the same predictor, and conflating them is a separate, common misreading:
| Predictor | Crude OR (95% CI) | Adjusted OR (95% CI) | p-value |
|---|---|---|---|
| Treatment A vs. B | 3.50 (2.02–6.06) | 2.15 (1.18–3.92) | 0.012 |
- Crude (unadjusted) OR comes from a bivariate model — the predictor alone against the outcome, with no other variables in the model. It can absorb the effect of confounders that happen to correlate with the predictor.
- Adjusted OR comes from a multivariable model that holds other specified covariates constant. It is the number to report as “independent of [the covariates actually in the model]” — never as “independent of confounding” in general, since a model only adjusts for what it explicitly includes.
In the table above, the drop from 3.50 crude to 2.15 adjusted indicates that part of the crude association was attributable to the covariates added to the model, not to the treatment itself. The sentence a results section would use: “After adjustment for [named covariates], Treatment A was associated with 2.15 times the odds of the outcome compared with Treatment B (adjusted OR 2.15, 95% CI 1.18–3.92, p = 0.012).” Report both numbers when both are available, and always state which covariates the adjusted model actually includes — “adjusted” with no covariate list named is not a complete result.
How to Report an Odds Ratio
A complete odds ratio statement needs four elements: the OR itself, its 95% confidence interval, what the reference category is, and (for a multivariable model) which covariates it’s adjusted for. Template: “[Group/exposure] had [OR value] times the odds of [outcome] compared with [reference group] (OR [value], 95% CI [lower]–[upper][, adjusted for covariates]).” Avoid “times more likely,” “times as likely,” or “% more likely to” unless the rare-disease assumption genuinely applies and you say so — when it doesn’t, those phrasings misstate an odds ratio as a risk ratio, exactly as shown in the worked example above.
How to Calculate an Odds Ratio From a 2×2 Table
For a 2×2 table with exposed cases (a), exposed non-cases (b), unexposed cases (c) and unexposed non-cases (d), the odds ratio is the cross-product ratio: OR = (a × d) / (b × c). In the worked example above, Treatment A has a = 60 complications and b = 40 without; Treatment B has c = 30 and d = 70. OR = (60 × 70) / (40 × 30) = 4,200 / 1,200 = 3.5, the same value reached by dividing the two odds. The cross-product form is handy because it works for any 2×2 table, including case-control data. To judge how precisely the 3.5 is estimated, see how to calculate a confidence interval for an odds ratio.
What Is a High Odds Ratio?
There is no single cut-off that makes an odds ratio “high.” How large an OR matters depends on the baseline risk, the width of the confidence interval and the clinical stakes. Two practical readings help. First, distance from 1 works in both directions: an OR of 0.5 and an OR of 2.0 are the same strength of association with the reference group flipped. Second, an OR can look large while the absolute change is small when the outcome is rare, and the OR overstates the risk ratio when the outcome is common. Judge size by the interval and the absolute risks, not the point estimate alone. The absolute risk reduction and NNT for the same data show what the change means in practice.
Converting an Odds Ratio to a Risk Ratio
When a cohort study reports an OR for a common outcome and you know the baseline risk p0 (the outcome incidence in the unexposed group), the Zhang and Yu correction gives an approximate risk ratio: RR = OR / (1 − p0 + p0 × OR), as documented for the ORToRelRisk function in the R DescTools package, citing Zhang and Yu (1998), JAMA 280(19):1690-1691. Check it on the worked example: OR = 3.5 and p0 = 0.30 give 3.5 / (0.70 + 1.05) = 2.0, the true risk ratio. The same OR implies different risk ratios at different baseline risks, which is why one OR cannot be translated without p0. The correction needs the incidence in the unexposed group, which a case-control sample cannot supply because its case-to-control ratio is fixed by the researcher.
If you pool odds ratios across strata of a confounder, the Mantel-Haenszel method gives a summary OR that is weighted by stratum. For the full contrast between the two measures, see odds ratio vs. risk ratio.
Odds and Probability Side by Side
Risk (probability) is bounded between 0 and 1, while odds run from 0 to infinity. The Cochrane Handbook (chapter 6, section 6.4.1) notes that a risk of 0.5 corresponds to odds of 1 and a risk of 0.95 to odds of 19, and that risk can be recovered from odds as risk = odds / (1 + odds). The MedCalc manual gives the same relationship from the other direction, odds = risk / (1 − risk).
| Risk (probability) | Odds | How to say it |
|---|---|---|
| 0.05 | 0.05 / 0.95 ≈ 0.053 | Odds and risk are close when the outcome is rare |
| 0.50 | 1.0 | Even odds |
| 0.80 | 4.0 | Four to one |
| 0.95 | 19 | Odds grow much faster than risk near 1 |
The stretch at the top of the scale is why odds ratios drift away from risk ratios as an outcome becomes common: a small rise in risk near 1 produces a very large rise in odds. The table above converts one group at a time. An odds ratio divides one group’s odds by the other’s, so it carries that stretch into the ratio.
A Second Worked Example: Smoking and Myocardial Infarction
The MedCalc manual uses a 2×2 table of 500 smokers and 500 non-smokers, in which 100 smokers and 20 non-smokers had a myocardial infarction:
| Infarction | No infarction | Total | |
|---|---|---|---|
| Smokers | 100 | 400 | 500 |
| Non-smokers | 20 | 480 | 500 |
- Risk: smokers 100/500 = 0.20; non-smokers 20/500 = 0.04. Risk ratio = 0.20 / 0.04 = 5.0.
- Odds: smokers 100/400 = 0.25; non-smokers 20/480 ≈ 0.0417. Odds ratio = (100 × 480) / (400 × 20) = 48,000 / 8,000 = 6.0.
- Risk difference: 0.20 − 0.04 = 0.16, so about 6 smokers per additional infarction (number needed to harm ≈ 1/0.16 = 6.25).
The outcome here is not extremely common (20% in the exposed group), yet the OR of 6.0 already exceeds the risk ratio of 5.0 by 20%. The gap in this example is smaller than in the first example, but the direction is the same, and the data table below shows how it grows with baseline risk.
When the Odds Ratio Is Below 1 and the Outcome Is Common
The distortion works in both directions. MedCalc and the Cochrane Handbook both state that an OR above 1 overstates the risk ratio and an OR below 1 understates the protective effect, and the Handbook adds that interpreting an odds ratio as a risk ratio can overstate the intervention effect in either direction. The Zhang and Yu formula used elsewhere on this page lets you check a below-1 case: with OR = 0.5 and a baseline risk p0 = 0.40, RR = 0.5 / (1 − 0.40 + 0.40 × 0.5) = 0.5 / 0.80 = 0.625. The reduction in risk is 37.5%, not the 50% that “0.5” invites readers to assume. Computed from the cited formula, not taken from a published study.
Which Outcome Is the Event?
An odds ratio for “death” and an odds ratio for “survival” in the same study are reciprocals of each other, so swapping the event and non-event simply inverts the OR. A risk ratio does not behave this way: the risk ratio for survival can differ greatly from the inverse of the risk ratio for death. The Cochrane Handbook (6.4.1.5) advises that the choice of which state is the “event” should be made deliberately, and notes a rule of thumb of focusing on the less common state. State clearly which outcome your OR refers to.
Zero Cells and Sparse Data
If one cell of the 2×2 table is zero, the odds ratio is 0 or undefined (a division by zero). The Cochrane Handbook (6.4.1.2) describes the standard remedy of adding 0.5 to every cell of the table, and notes that a study with no events in either group is omitted from the odds ratio calculation because it carries no information about the ratio. Whenever a correction is used, say so in the methods.
Why Absolute Measures Still Matter
An odds ratio, like any relative measure, hides the baseline. The Cochrane Handbook (6.4.1.4) points out that a risk difference of 2 percentage points can be trivial (a rise from 58% to 60%) or substantial (a rise from 1% to 3%), depending on context. The MedCalc manual makes the same point through the number needed to treat: a fall in risk from 40% to 20% gives an NNT of 5, while a fall from 2% to 1% gives an NNT of 100, although both halve the risk. Because odds ratios are harder to interpret than risks, the Handbook recommends expressing results in the context of a typical baseline risk and giving the absolute difference. The data table below fixes the odds ratio at 2.0 and shows how the implied risk ratio and exposed-group risk change with baseline risk.
When to Report a Risk Ratio Instead
Use a risk ratio when the design gives you real incidence in both groups (a cohort study or randomized trial) and readers will interpret the result as a change in probability. Use an odds ratio when the design cannot yield a risk ratio (case-control sampling) or when you are reporting logistic regression coefficients, which exponentiate to odds ratios. In the second case, supply predicted or absolute risks alongside, so that readers are not left to convert odds themselves.
Frequently Asked Questions
Is an odds ratio the same as relative risk?
No. Relative risk (risk ratio) compares probabilities directly; an odds ratio compares odds. They converge only when the outcome is rare in both groups being compared (the rare-disease assumption); when the outcome is common, as in the worked example above, the OR is always further from 1.0 than the true RR in the same direction — it overstates the effect if read as a risk ratio.
What does an odds ratio of exactly 1 mean?
No association — the odds of the outcome are identical between the group being compared and the reference group. Whether an OR near but not exactly 1 is distinguishable from “no association” is a question for the confidence interval, not the point estimate alone.
Can an odds ratio be negative?
No. An odds ratio is a ratio of two positive quantities and is always greater than 0. It ranges from 0 (the outcome never occurs in the comparison group when it does occur in the reference group) through 1 (no association) to unbounded positive values. What can be negative is the log-odds coefficient a logistic regression model actually estimates before it’s exponentiated into the odds ratio you read in results tables.
Why do case-control studies report odds ratios instead of relative risk?
Because a case-control design selects participants by outcome status (a fixed number of cases and controls, chosen by the researcher) rather than following an exposed and unexposed population forward in time, true incidence — and therefore a valid risk ratio — cannot be calculated from the sample. The odds ratio is the measure of association the design can legitimately produce, and under the rare-disease assumption it approximates the risk ratio a cohort study would have shown.
Is a bigger sample size enough to trust a wide odds-ratio confidence interval?
No — interval width reflects the precision of the specific estimate (driven by the number of outcome events, not just total sample size), and a wide interval that still excludes 1.0 can be statistically significant while remaining too imprecise to be practically useful. Report the interval alongside the point estimate rather than the point estimate alone, and treat a CI that spans 1.0 as “not distinguishable from no association” regardless of how far the point estimate sits from 1.0.
How do I convert an odds ratio to a percentage?
(OR − 1) × 100 gives the percentage change in the odds, so OR = 1.5 is 50% higher odds and OR = 0.68 is 32% lower odds. That is not a percentage change in risk. To express the result as risk you need the baseline risk, then apply RR = OR / (1 − p0 + p0 × OR).
Why is the odds ratio further from 1 than the risk ratio?
Because odds are risk / (1 − risk), the odds grow faster than the risk as the risk rises. The more common the outcome, the more the ratio of odds exceeds the ratio of risks, in the direction away from 1. In the smoking example above, the risk ratio is 5.0 and the odds ratio 6.0.
When should I report a risk ratio instead of an odds ratio?
When your design provides incidence in both groups and the outcome is common, a risk ratio avoids the overstatement shown above. See the section on when to report a risk ratio, and the odds ratio vs. risk ratio comparison.
Sources
Sources:
- Cochrane Handbook for Systematic Reviews of Interventions, chapter 6, section 6.4.1: https://www.cochrane.org/authors/handbooks-and-manuals/handbook/current/chapter-06
- MedCalc Software, Risk, odds and effect measures: https://www.medcalc.org/en/book/risk-odds.php
- DescTools, ORToRelRisk (Zhang and Yu 1998 formula): https://rdrr.io/cran/DescTools/man/ORToRelRisk.html
Related CASRAI Resources
Data: Risk ratio implied by an odds ratio of 2.0 at different baseline risks
Computed with the Zhang and Yu (1998) conversion RR = OR / (1 - p0 + p0 x OR), as documented in the R DescTools ORToRelRisk help page, for a fixed OR of 2.0 across baseline (unexposed-group) risks; exposed-group risk is RR x p0. Risk and odds definitions follow the Cochrane Handbook chapter 6 and the MedCalc manual. Overstatement is OR divided by RR.
| Scenario | Odds ratio | Baseline risk (unexposed) (%) | Implied exposed-group risk (%) | Implied risk ratio | OR divided by RR |
|---|---|---|---|---|---|
| OR 2.0 at baseline risk 1% | 2 | 1 | 2 | 1.98 | 1.01 |
| OR 2.0 at baseline risk 5% | 2 | 5 | 9.5 | 1.9 | 1.05 |
| OR 2.0 at baseline risk 10% | 2 | 10 | 18.2 | 1.82 | 1.1 |
| OR 2.0 at baseline risk 20% | 2 | 20 | 33.3 | 1.67 | 1.2 |
| OR 2.0 at baseline risk 30% | 2 | 30 | 46.2 | 1.54 | 1.3 |
| OR 2.0 at baseline risk 40% | 2 | 40 | 57.1 | 1.43 | 1.4 |
| OR 2.0 at baseline risk 60% | 2 | 60 | 75 | 1.25 | 1.6 |
Sources
- DescTools ORToRelRisk (Zhang and Yu 1998 formula) (accessed 2026-11-18)
- Cochrane Handbook ch. 6, section 6.4.1 (accessed 2026-11-18)
- MedCalc: Risk, Odds and Effect Measures (accessed 2026-11-18)
Compiled by CASRAI from the sources above. Free to reuse under CC BY 4.0 with attribution.







