Open StatClinic →
📊 Epidemiology & Biostatistics

Relative Risk vs Odds Ratio in Medical Research: What Is the Difference?

🕑 22 min read 📅 July 2026 ✅ Peer-reviewed content 📚 3300+ words
S
StatClinic Editorial Team Statistical content for medical researchers and clinicians
Relative risk and odds ratio are the two most widely reported effect measures in clinical research, yet they are consistently confused — sometimes by junior researchers who use the terms interchangeably, sometimes by experienced clinicians who misread OR as RR without realising the magnitude distortion this causes. The distinction is not merely semantic. For a common outcome such as 30-day hospital readmission at 25%, an odds ratio of 3.0 corresponds to a relative risk of only 1.88. A clinician acting on OR = 3.0 as if it were a relative risk overestimates the true effect of the exposure by 60%. This guide explains both measures from first principles, shows exactly why they diverge, provides four full clinical examples with side-by-side calculations, and gives you the rules for choosing which measure to report in each study design.

Definitions: Probability, Risk, and Odds

Before comparing relative risk and odds ratio, you need to be clear on three foundational concepts that underpin both measures: probability, risk, and odds. These three quantities describe the same underlying phenomenon — how often an event occurs — but express it in different scales.

Probability and Risk

Probability (or risk, when applied to disease development) is the number of people who experience the event divided by the total number of people in the group. If 30 out of 100 smokers develop hypertension over 10 years, the risk is 30/100 = 0.30, or 30%. Risk is always between 0 and 1 (or 0% and 100%).

Odds

Odds express the same information differently: the number of people who experience the event divided by the number who do not. From the same example, if 30 smokers develop hypertension and 70 do not, the odds are 30/70 = 0.43 — or equivalently, "43 events for every 100 non-events." Odds are always positive and have no upper bound: they can be 0.01, 1.0, 5.0, or 100.

Converting Between Probability, Risk, and Odds
Odds = P ÷ (1 − P)   |   P = Odds ÷ (1 + Odds)
P = 0.05 (5%) → Odds = 0.05/0.95 = 0.053
P = 0.10 (10%) → Odds = 0.10/0.90 = 0.111
P = 0.25 (25%) → Odds = 0.25/0.75 = 0.333
P = 0.50 (50%) → Odds = 0.50/0.50 = 1.000
P = 0.75 (75%) → Odds = 0.75/0.25 = 3.000
P = 0.90 (90%) → Odds = 0.90/0.10 = 9.000

Notice how probability and odds track closely at low values (5% vs 0.053) but diverge dramatically at high values (90% vs 9.000). This divergence is the root cause of the difference between relative risk and odds ratio when outcomes are common.

What Is Relative Risk?

Relative risk (RR), also called the risk ratio, is the ratio of the probability of an outcome in the exposed group to the probability of the same outcome in the unexposed group. It directly compares two risks.

📈 Relative Risk (RR)
RR = Risk(exposed) / Risk(unexposed)
= [a/(a+b)] / [c/(c+d)]
Null value = 1.0  |  Range: 0 to ∞
Requires knowing both absolute risks
Valid for cohort studies and RCTs
📊 Odds Ratio (OR)
OR = Odds(exposed) / Odds(unexposed)
= (a × d) / (b × c)
Null value = 1.0  |  Range: 0 to ∞
Only needs exposure-disease cross-tabulation
Valid for all designs; required for case-control

The RR interpretation is intuitive: RR = 2 means the exposed group has twice the risk compared to the unexposed group. RR = 0.5 means the exposed group has half the risk — a 50% risk reduction. Clinicians, policy-makers, and patients understand relative risk naturally.

When RR is the right measure Relative risk requires both absolute risks: you need to know what proportion of exposed people developed the outcome AND what proportion of unexposed people did. This is only possible in study designs where you follow groups prospectively: cohort studies and randomised controlled trials. In these designs, you observe who develops disease and who does not across groups, giving you the numbers needed for both the numerator and denominator of the risk ratio.

What Is Odds Ratio?

The odds ratio (OR) is the ratio of the odds of an outcome in the exposed group to the odds of the outcome in the unexposed group. It is calculated from a 2×2 contingency table using the cross-product formula:

Odds Ratio — Cross-Product Formula
OR = (a × d) / (b × c)
a = exposed cases (exposed AND disease+)
b = exposed controls (exposed AND disease−)
c = unexposed cases (unexposed AND disease+)
d = unexposed controls (unexposed AND disease−)

The OR has a crucial mathematical property: it is invariant to the sampling ratios in a case-control study. If you enrol twice as many controls, the OR calculated from the table remains the same (the RR calculated from the same table would change). This invariance makes OR the only valid measure when cases and controls are selected in researcher-determined ratios that do not reflect the natural disease frequency — exactly the situation in case-control studies.

The OR is also the natural output of binary logistic regression. Every Exp(B) value in SPSS output is an odds ratio, not a relative risk. Logistic regression is the most widely used multivariable method for binary outcomes, which explains why ORs appear in the majority of observational medical literature.

The Symmetry Property of OR The OR has a unique symmetry: you can calculate it as (odds of disease given exposure) / (odds of disease given no exposure) OR as (odds of exposure given disease) / (odds of exposure given no disease) — and you get the same number. This means OR from a case-control study, where you look at exposure rates among cases and controls, equals the OR that would be calculated in a cohort study looking at disease rates among exposed and unexposed. RR does not have this property.

Key Mathematical Differences

The critical mathematical relationship between OR and RR depends on the baseline risk (outcome frequency in the unexposed group). The formula connecting them is:

Converting OR to RR — Zhang & Yu Formula (1998)
RR = OR / [ (1 − P₀) + (P₀ × OR) ]
OR = calculated odds ratio from your study
P₀ = outcome probability in the unexposed group (baseline risk)
As P₀ approaches 0 (rare disease), denominator → (1−0) + (0×OR) = 1, so RR → OR

This formula reveals everything you need to know about when OR and RR diverge. When P₀ is near zero, the denominator is approximately 1, and RR ≈ OR. When P₀ is large (common disease), the denominator grows, and RR becomes substantially smaller than OR for positive associations (OR > 1), or larger than OR for protective associations (OR < 1).

Numerical Illustration: How OR and RR Diverge by Baseline Risk

Suppose OR = 3.0 in all cases. Watch what happens to the corresponding RR as baseline risk in the unexposed group increases:

P₀ = 5%
RR = 2.73
Relative risk
OR = 3.00
Odds ratio
▲ 10% overestimate
P₀ = 15%
RR = 2.35
Relative risk
OR = 3.00
Odds ratio
▲ 28% overestimate
P₀ = 30%
RR = 1.88
Relative risk
OR = 3.00
Odds ratio
▲ 60% overestimate
P₀ = 50%
RR = 1.50
Relative risk
OR = 3.00
Odds ratio
▲ 100% overestimate

When the unexposed group baseline risk is 50%, an OR of 3.0 corresponds to a true RR of only 1.5. Reporting OR = 3.0 as if it were a relative risk doubles the apparent magnitude of the association. This is not an edge case — baseline risks of 20–40% are common for outcomes like hospital readmission, postoperative complications, medication adherence, and chronic disease recurrence.

The Rule of Thumb When outcome prevalence or incidence in the unexposed group exceeds 10%, OR and RR diverge meaningfully. The higher the baseline risk, the greater the divergence. For outcomes with baseline risk above 20%, an OR > 1 will overestimate the corresponding RR by at least 25%. For outcomes above 40%, the overestimation may exceed 50%.

The Rare Disease Assumption: When OR ≈ RR

The rare disease assumption states that when the outcome is sufficiently rare — typically defined as less than 10% incidence or prevalence — the odds ratio closely approximates the relative risk. This is the theoretical justification for using OR from case-control studies to infer population-level relative risks.

The mathematics: when P is small, 1 − P ≈ 1. Therefore:

Odds = P / (1−P) ≈ P / 1 = P when P is small

So odds ≈ probability ≈ risk when the disease is rare. This means the OR — a ratio of two odds — approximates the RR — a ratio of two probabilities — when both probabilities are small. The assumption holds well below 10% and reasonably well below 15%, after which the approximation begins to fail.

Historical Importance The rare disease assumption was foundational to early epidemiology when many conditions studied were genuinely rare (infectious diseases, specific cancers, uncommon occupational diseases). It allowed case-control studies — efficient for studying rare diseases — to produce results directly interpreted as relative risk estimates. Today, case-control studies are increasingly used for conditions that are not rare, making awareness of the assumption more critical than ever.

Study Design and the Choice of Measure

The single most important factor determining whether you should use RR or OR is your study design. This is not a stylistic choice — it is a validity issue.

Study Design Can You Calculate RR? Correct Primary Measure Reason
Case-control study No OR Case:control ratio set by researcher — does not reflect natural risk
Cohort study — rare outcome (<10%) Yes RR (or OR — similar) OR ≈ RR; both valid; RR more intuitive
Cohort study — common outcome (>10%) Yes RR preferred OR overestimates; RR or risk difference more interpretable
Randomised controlled trial Yes RR, risk difference, or NNT Absolute and relative risk can both be calculated; NNT adds clinical utility
Cross-sectional study Yes (prevalence ratio) Prevalence ratio (PR) or OR PR is the RR equivalent for cross-sectional prevalence data; OR acceptable
Logistic regression (any design) Not directly OR (Exp[B]) Logistic regression produces ORs; use log-binomial for adjusted RR
Meta-analysis of case-control studies No Pooled OR Individual studies only have ORs — RRs cannot be pooled across case-control designs

Logistic Regression: An Important Special Case

When researchers run binary logistic regression on cohort data — which is extremely common because of logistic regression's flexibility for confounding adjustment — the output is always an OR, even though the underlying study design could support RR calculation. This creates a problematic situation when the outcome is common: the ORs from the regression model overestimate the corresponding RRs.

Three solutions exist for this problem:

Clinical Examples: RR and OR Calculated Side by Side

The following four examples calculate both RR and OR from the same data, making the divergence visible and clinically concrete.

1

Smoking and Lung Cancer — Rare Outcome (OR ≈ RR)

Cohort study over 20 years • Outcome: lung cancer (rare: ~10% in smokers) • Illustrates OR ≈ RR when disease is rare

Lung Cancer (+)No Cancer (−)Total
SmokeSmoker120 (a)1080 (b)1200
Non-smoker30 (c)1770 (d)1800
Total15028503000
Relative Risk (RR) Risk(smokers) = 120/1200 = 0.100 (10.0%)
Risk(non-smokers) = 30/1800 = 0.0167 (1.67%)
RR = 0.100 / 0.0167 = RR = 5.99 ≈ 6.0
Odds Ratio (OR) OR = (120 × 1770) / (1080 × 30) = 212,400 / 32,400 = OR = 6.56
Discrepancy OR overestimates RR by: (6.56 − 6.0) / 6.0 × 100 = 9.3% — modest, as expected for ~10% baseline risk
Conclusion: With a lung cancer rate of 10% in smokers — near the boundary of "rare" — OR = 6.56 overestimates RR = 6.0 by only 9%. For all practical purposes, these are comparable and either could be reported. However, if this were a case-control study, only the OR would be validly interpretable. The closeness of OR and RR here validates the rare disease assumption at the 10% boundary.
2

Obesity and Surgical Complication — Common Outcome (OR Substantially Overestimates RR)

Prospective cohort • Outcome: postoperative complication (common: 30% baseline) • Shows OR-RR divergence at high baseline risk

Complication (+)No Complication (−)Total
BMIObese (BMI≥30)168 (a)232 (b)400
Non-obese180 (c)420 (d)600
Total3486521000
Relative Risk (RR) Risk(obese) = 168/400 = 0.420 (42.0%)
Risk(non-obese) = 180/600 = 0.300 (30.0%) ← P₀ = 0.30
RR = 0.420 / 0.300 = RR = 1.40
Odds Ratio (OR) OR = (168 × 420) / (232 × 180) = 70,560 / 41,760 = OR = 1.69
Verification via Zhang & Yu RR = 1.69 / [(1−0.30) + (0.30×1.69)] = 1.69 / [0.70 + 0.507] = 1.69 / 1.207 = 1.40 ✓
Discrepancy OR overestimates RR by: (1.69 − 1.40) / 1.40 × 100 = 20.7% — substantial divergence
Why This Matters Clinically A paper reporting OR = 1.69 for obesity and surgical complications would be read by a clinician as "obesity increases complication risk by 69%." The true risk increase is only 40%. This 29 percentage-point overstatement could distort risk counselling, resource allocation, and policy decisions. For a common outcome like 30% baseline complication risk, OR should not be used as a proxy for RR without explicit conversion.
Correct reporting: In a cohort study with direct risk measurement, RR = 1.40 (95% CI 1.18–1.65) should be the headline measure, not OR = 1.69. If logistic regression is used for adjustment, state: "Adjusted OR 1.69 corresponds to an approximate adjusted RR of 1.40 after applying Zhang & Yu conversion with baseline risk 30%."
3

Breastfeeding and Infant Otitis Media — Protective Association

Prospective cohort • Protective exposure • Shows OR underestimates protective RR (OR further from 1 in the protective direction)

Otitis Media (+)No Otitis Media (−)Total
FeedBreastfed (≥6 months)45 (a)255 (b)300
Formula-fed110 (c)390 (d)500
Total155645800
Relative Risk (RR) Risk(breastfed) = 45/300 = 0.150 (15.0%)
Risk(formula-fed) = 110/500 = 0.220 (22.0%) ← P₀ = 0.22 (reference = formula-fed)
RR = 0.150 / 0.220 = RR = 0.682
Odds Ratio (OR) OR = (45 × 390) / (255 × 110) = 17,550 / 28,050 = OR = 0.626
Discrepancy for Protective Associations RR = 0.68 (32% risk reduction)   OR = 0.63 (37% odds reduction)
OR exaggerates the protective effect: 37% vs 32% — OR inflates protection for common outcomes
Direction of bias for OR < 1: For protective exposures (OR < 1), the OR is further from 1 than the RR, meaning it overestimates the degree of protection when the outcome is common. Breastfeeding shows a true 32% risk reduction (RR), but OR suggests a 37% reduction in odds. The OR is the "more protective looking" statistic, but it overstates the true effect. This is the mirror image of the harmful association overestimation.
4

Diabetes and Peripheral Neuropathy — Case-Control Study (Only OR Valid)

Hospital case-control study • Only OR valid by design • OR approximates RR because outcome is rare in the population

Neuropathy CasesControlsTotal
DMDiabetes110 (a)72 (b)182
No diabetes70 (c)108 (d)178
Total180180360
What we CAN calculate OR = (110 × 108) / (72 × 70) = 11,880 / 5,040 = OR = 2.36
95% CI: SE(ln OR) = √(1/110+1/72+1/70+1/108) = √0.04639 = 0.2153
95% CI = e^(0.859 ± 0.422) = 1.54 to 3.62
What we CANNOT calculate Apparent risk in "cases" row = 110/182 = 60.4% — but this reflects our 1:1 sampling, not population risk
If we had enrolled 1:4 (cases:controls), this "risk" would be ~20% — not the same disease. The OR would remain 2.36.
Why OR is the Only Option Here The 60% "prevalence" of diabetes among cases in this table does not mean 60% of people with neuropathy have diabetes in the population. It means exactly 110 out of our 180 enrolled cases had diabetes — a number we chose when we sampled 180 cases. The only valid measure is OR = 2.36. Since peripheral neuropathy is a relatively rare condition in the general population (prevalence ~2–5%), OR ≈ RR by the rare disease assumption, and we may state that patients with diabetes have approximately 2.4 times higher risk of peripheral neuropathy.
Journal reporting: "Diabetes was significantly associated with peripheral neuropathy in this case-control study (OR 2.36, 95% CI 1.54–3.62, p < 0.001). Given the low population prevalence of peripheral neuropathy (<5%), the OR approximates the relative risk."

Side-by-Side Comparison: Complete Reference Table

Feature Relative Risk (RR) Odds Ratio (OR)
What it measures Ratio of two probabilities (risks) Ratio of two sets of odds
Formula [a/(a+b)] / [c/(c+d)] (a × d) / (b × c)
Null value 1.0 1.0
Range 0 to ∞ (but bounded by P₀) 0 to ∞ (unconstrained)
Valid study designs Cohort studies, RCTs, cross-sectional All designs; required for case-control
Logistic regression Not produced directly (need log-binomial) Direct output — Exp(B) in SPSS
Rare disease (<10%) More intuitive ≈ RR; both acceptable
Common disease (>10%) Preferred; accurately reflects effect Overestimates RR if OR > 1; use with caution
Protective associations (OR <1) Accurately reflects risk reduction Overestimates protection (appears lower than true RR)
Intuitive for clinicians Yes — directly answers "how much more likely?" Less intuitive — requires understanding of odds
Meta-analysis of case-control studies Cannot be pooled from case-control data Standard pooled measure
Symmetry property Not symmetric Symmetric — invariant to sampling design
Conversion to other measure RR → OR: complex OR → RR: Zhang & Yu formula with P₀

When the Odds Ratio Overestimates: Recognising the Problem in Published Papers

Several contextual clues should alert you that an OR reported in a paper likely overestimates the true relative risk:

1

Outcome prevalence or incidence is above 10%

Any time the outcome occurs in more than 10% of the reference group, the OR will meaningfully exceed the RR for positive associations. Check the event rates in the methods or baseline characteristics table. Outcomes like postoperative complications, medication adherence, hospital readmission, comorbidity recurrence, and quality-of-life endpoints often exceed 20–40% baseline risk.

2

The design is cohort or cross-sectional but the authors report ORs from logistic regression

This is the most common scenario in the literature. Logistic regression is applied to cohort or cross-sectional data — producing ORs — even though both the design and the data support direct RR calculation. The authors may not acknowledge the overestimation, especially if the outcome is common.

3

The OR is large (e.g., OR > 2.5) and the outcome is common

Large ORs amplify the divergence from RR. An OR of 4.0 with baseline risk 30% in the unexposed group corresponds to RR = 4.0 / [(1−0.30) + 0.30×4.0] = 4.0/1.90 = 2.10. The OR says four times higher odds; the true risk is only 2.1 times higher. A clinician reading OR = 4.0 would be very alarmed; the true RR = 2.1 would be concerning but substantially less dramatic.

4

The paper confusingly uses "risk" language alongside ORs

Phrases like "patients with diabetes were 2.4 times more likely to develop the complication (OR 2.4)" conflate OR language (odds ratio) with RR language (times more likely = risk ratio). The OR of 2.4 is not the same as saying the risk is 2.4 times higher — unless the outcome is rare. When you see this in a paper, check the outcome frequency and apply the conversion formula if needed.

Common Interpretation Mistakes

Mistake 1: Treating OR as RR when reporting results to patients or policy-makers

Clinicians communicating risk to patients — "this medication triples your risk" when the study found OR = 3.0 — may be substantially exaggerating for common outcomes. If the baseline outcome risk is 25%, OR = 3.0 corresponds to RR = 1.88, meaning the medication nearly doubles risk — not triples it. This discrepancy affects informed consent and shared decision-making.

✓ Fix: Always check the outcome frequency before translating OR into clinical communication. Apply the Zhang & Yu conversion for common outcomes. Use absolute risk increase (ARI = risk(exposed) − risk(unexposed)) for patient-facing communication alongside relative measures.

Mistake 2: Computing RR from a case-control table and reporting it as relative risk

Calculating risk as a/(a+b) in a case-control study and reporting it as "relative risk" is a fundamental error. The apparent risk in the case row is determined by how many cases were enrolled, not by actual disease incidence. If you enrolled twice as many cases, the apparent "risk" in the exposed group would double, but the OR would remain the same. Any RR calculated from case-control proportions is meaningless.

✓ Fix: In case-control studies, report only the OR. State explicitly: "Risk ratios cannot be calculated from this case-control design. The odds ratio of 2.36 (95% CI 1.54–3.62) approximates the relative risk given the low disease prevalence in the source population."

Mistake 3: Ignoring the OR-RR distinction in systematic reviews and meta-analyses

Meta-analyses pooling odds ratios from logistic regression across multiple cohort studies produce pooled ORs that are potentially inflated estimates of the true pooled RR. This problem compounds when studies with different baseline risks are pooled: each study's OR overestimates its own RR by a different amount, making the pooled OR a distorted summary of the underlying risk relationships.

✓ Fix: In systematic reviews and meta-analyses, explicitly note whether the pooled estimate is an OR or RR, and report baseline risk frequencies from the included studies. For common outcomes, consider requesting or computing individual-study RRs before pooling, or use the Zhang & Yu conversion study by study.

Mistake 4: Assuming that OR and RR always move in the same direction by the same amount

While OR and RR are always on the same side of the null value (both above 1 or both below 1 for the same association), their magnitudes diverge in predictable but non-linear ways. An OR that decreases from 2.0 to 1.5 after adjustment may correspond to a change in RR from 1.75 to 1.40 in different amounts for different baseline risks. Comparing changes in OR across studies with different baseline risks is not straightforward.

✓ Fix: When comparing OR estimates across studies or between crude and adjusted models, apply consistent conversion using the study-specific baseline risks, or restrict comparisons of effect magnitude to studies with similar outcome frequencies. Alternatively, compare risk differences (absolute) rather than relative measures.

Mistake 5: Concluding that RR is always preferable and OR should be abandoned

Some researchers, upon learning about OR overestimation, conclude that OR should never be reported. This overcorrects. OR is the only valid measure for case-control studies, the natural output of logistic regression (the most powerful tool for multivariable adjustment of binary outcomes), and a technically superior measure for meta-analysis because of its symmetry properties. For rare diseases, OR and RR are interchangeable. OR should be reported with appropriate context about the outcome frequency, not abandoned.

✓ Fix: Match the measure to the study design and outcome frequency. Use RR when available from cohort/RCT data with common outcomes. Use OR when the design requires it (case-control) or when logistic regression is the adjustment method. Always report the baseline outcome risk so readers can apply the conversion if needed.

Reporting Examples in Medical Journals

The following examples show how to correctly report RR and OR in different contexts, including the language that signals which measure is being used and how the study design justifies the choice.

Cohort Study — Reporting RR as Primary Measure
"Over the 10-year follow-up period, the incidence of myocardial infarction was 8.2% (82/1000) in heavy smokers compared with 2.4% (24/1000) in never-smokers (relative risk 3.42, 95% CI 2.18–5.36, p < 0.001). The absolute risk difference was 5.8% (95% CI 3.9–7.7%), corresponding to a number needed to harm of 17 (one additional MI for every 17 people who smoke heavily for 10 years)."
Case-Control Study — Reporting OR with Rare Disease Justification
"Helicobacter pylori infection was significantly associated with gastric cancer in this case-control study (OR 4.20, 95% CI 2.65–6.66, p < 0.001). Given the low population incidence of gastric cancer (approximately 2–3 per 100,000 per year), the odds ratio approximates the relative risk, suggesting that H. pylori infection confers approximately four times higher risk of gastric cancer compared with uninfected individuals."
Cohort Study with Logistic Regression — Common Outcome, Acknowledging Limitation
"Multivariable logistic regression adjusting for age, sex, and comorbidities showed that antibiotic use was associated with increased risk of Clostridioides difficile infection (adjusted OR 3.10, 95% CI 1.87–5.13). Given the 22% rate of C. difficile in the reference group (non-antibiotic users), this OR overestimates the true relative risk. Applying the Zhang and Yu conversion (Zhang J, Yu KF, 1998), the estimated adjusted relative risk is approximately 2.21 (95% CI 1.57–3.12)."
Randomised Trial — RR Alongside Risk Difference
"At 90 days, death or disability occurred in 18.4% of patients in the treatment group and 28.6% in the control group. Treatment was associated with a significant reduction in the primary outcome (relative risk 0.64, 95% CI 0.51–0.81, p < 0.001; absolute risk reduction 10.2%, 95% CI 5.8–14.6%; number needed to treat 10, 95% CI 7–17). The unadjusted odds ratio was 0.57 (95% CI 0.43–0.75), consistent with the 28.6% baseline event rate producing an OR more extreme than the RR."

Frequently Asked Questions

What is the main difference between relative risk and odds ratio? +
Relative risk (RR) compares two probabilities: probability of outcome in the exposed group divided by probability in the unexposed group. Odds ratio (OR) compares two odds: odds of outcome in the exposed group divided by odds in the unexposed group. When the outcome is rare (below 10%), OR ≈ RR numerically. When the outcome is common (above 10%), OR is further from 1 than RR — it overestimates the association for harmful exposures and overstates the protection for protective ones.
When should you use relative risk instead of odds ratio? +
Use relative risk in cohort studies and randomised trials where both the exposed and unexposed groups are followed prospectively and absolute risks can be measured directly. RR is more intuitive and does not overestimate associations for common outcomes. Use odds ratio in case-control studies (where RR is not calculable from design) and when reporting logistic regression results. For logistic regression on cohort data with common outcomes, consider converting OR to RR using the Zhang & Yu formula or using log-binomial regression instead.
Why does odds ratio overestimate relative risk for common outcomes? +
The overestimation comes from the mathematical relationship: odds = P / (1−P). When P is small, (1−P) ≈ 1, so odds ≈ probability, and therefore OR ≈ RR. When P is large, (1−P) becomes small, making the denominator shrink and odds grow faster than probability. This means the ratio of two large odds (OR) is always further from 1.0 than the ratio of the two corresponding probabilities (RR). The larger the baseline risk and the larger the OR, the greater the overestimation of RR by OR.
Can you calculate relative risk from a case-control study? +
No — not directly and validly. In a case-control study, the investigator chooses how many cases and controls to enrol. This choice determines the apparent "risk" proportions in the table, not the natural disease frequency in the population. Calculating RR from the apparent proportions in a case-control table produces a meaningless number that changes whenever the case:control ratio changes. Only the odds ratio remains invariant to the sampling design. When disease is rare, OR from a case-control study can be interpreted as an approximation of the population RR.
What is the rare disease assumption? +
The rare disease assumption states that when disease incidence or prevalence is low — typically below 10% — the OR closely approximates the RR. Mathematically: when probability P is small, odds = P/(1−P) ≈ P. So odds ≈ risk, and therefore OR ≈ RR. This assumption justifies using OR from case-control studies as a proxy for the population RR. It was foundational to early epidemiology but is increasingly challenged as case-control studies are applied to common conditions where the assumption fails.
How do you convert odds ratio to relative risk? +
Use the Zhang & Yu (1998) formula: RR = OR / [(1 − P₀) + (P₀ × OR)] where P₀ is the outcome probability in the unexposed reference group. Example: OR = 2.5, P₀ = 0.30 (30% baseline risk). RR = 2.5 / [(1−0.30) + (0.30×2.5)] = 2.5 / [0.70 + 0.75] = 2.5 / 1.45 = 1.72. The OR of 2.5 corresponds to a true RR of only 1.72 when baseline risk is 30% — a 45% overestimate if OR is read as RR.
Which is better to report, relative risk or odds ratio? +
Neither is universally better — the choice depends on study design and outcome frequency. RR is preferred when the design supports it (cohort, RCT) and the outcome is common, because it accurately reflects the true risk difference and is more clinically intuitive. OR is required for case-control studies and is the natural output of logistic regression. For rare outcomes in any design, OR and RR are numerically similar, so the distinction matters little. The key is to match the measure to the design, report baseline risk frequencies, and acknowledge OR-RR divergence when it is clinically meaningful.
What does it mean when RR equals 2 but OR equals 3 for the same data? +
This situation arises when the outcome is common in the unexposed group. RR = 2 means the exposed group has twice the probability of the outcome — the risk doubles. OR = 3 from the same data means the exposed group has three times the odds. A reader who misreads OR as RR perceives a tripling of risk when the actual risk only doubles. The larger the baseline risk, the wider the gap between OR and RR. This is one of the most clinically consequential statistical misinterpretations in the medical literature.
Does logistic regression produce relative risk or odds ratio? +
Binary logistic regression produces odds ratios. The Exp(B) column in SPSS output is the OR for each predictor. To obtain adjusted relative risks directly from regression, use log-binomial regression (SPSS: Generalized Linear Models, Binary outcome, Log link, Binomial distribution) or modified Poisson regression with robust standard errors. These alternatives are preferred when the outcome is common and accurate RR estimation is needed. If logistic regression must be used, apply the Zhang & Yu conversion to the OR with the reference group outcome probability.
Is the risk ratio the same as relative risk? +
Yes — risk ratio and relative risk are interchangeable terms that refer to the same measure: the ratio of the probability of an outcome in the exposed group to the probability in the unexposed group. Some journals and textbooks prefer "risk ratio" to avoid implying causation (ratio is neutral; "relative risk" implies an actual risk relationship). Clinical trial literature often uses "risk ratio" alongside absolute risk reduction (ARR) and number needed to treat (NNT). In epidemiology, "relative risk" is the historical term and remains common.

Calculate RR and OR from your data instantly

StatClinic's free calculators compute both relative risk and odds ratio from 2×2 tables, with 95% CI, chi-square test, and plain-English interpretation for thesis and journal submission.

Open Relative Risk Calculator →