{
  "id": "odds-ratio",
  "title": "Odds Ratio",
  "lang": "en",
  "source_lang": "en",
  "summary": "An odds ratio compares the odds of an event between two groups and measures association between binary variables.",
  "category": "mathematics",
  "subcategory": "probability-statistics",
  "type": "concept",
  "aliases": [
    "OR",
    "cross-product ratio",
    "relative odds"
  ],
  "generated_at": "2026-10-04",
  "model": "pro/gpt-6.1-sol",
  "url": "https://aiwiki.page/en/odds-ratio/",
  "translations": {
    "zh-Hans": {
      "url": "https://aiwiki.page/zh/odds-ratio/",
      "json": "https://aiwiki.page/zh/odds-ratio.json"
    }
  },
  "sections": [
    {
      "heading": "",
      "text": "The odds ratio (OR) is a measure in statistics that compares the odds of an event in one group with its odds in another. Unlike a ratio of probabilities, it compares each event probability with the probability of its complement before taking the ratio. It is widely used to describe associations between binary variables, especially in epidemiology, case–control studies, and logistic regression. (online.stat.psu.edu)"
    },
    {
      "heading": "Definition and interpretation",
      "text": "For an event with probability \\(p\\), its odds are\n\n\\[\\operatorname{odds}(p)=\\frac{p}{1-p}.\\]\n\nIf the event probabilities in groups 1 and 0 are \\(p_1\\) and \\(p_0\\), respectively, their odds ratio is\n\n\\[\\mathrm{OR} =\\frac{p_1/(1-p_1)}{p_0/(1-p_0)} =\\frac{p_1(1-p_0)}{p_0(1-p_1)}.\\]\n\nFor probabilities strictly between 0 and 1, the ratio is positive and finite. An OR of 1 indicates equal odds; values above 1 indicate greater odds in group 1, and values below 1 indicate lower odds. For example, OR \\(=2\\) means twice the odds—not necessarily twice the probability. The reference group and the event being counted must therefore be specified. (online.stat.psu.edu)"
    },
    {
      "heading": "Calculation from a contingency table",
      "text": "For two binary variables, observations can be arranged in a contingency table:\n\n | Event | No event\nGroup 1 | \\(a\\) | \\(b\\)\nGroup 0 | \\(c\\) | \\(d\\)\n\nThe sample odds ratio is\n\n\\[\\widehat{\\mathrm{OR}} =\\frac{a/b}{c/d} =\\frac{ad}{bc}.\\]\n\nThis expression explains the alternative name cross-product ratio. It can also be written as \\((a/c)/(b/d)\\): exchanging the roles of the two variables leaves the value unchanged. Reversing either the group labels or the event labels replaces it with its reciprocal; reversing both leaves it unchanged. At the population level, with positive cell probabilities, OR \\(=1\\) is equivalent to statistical independence of the two binary variables. (online.stat.psu.edu)\n\nAs an arithmetic illustration, suppose 40 of 100 observations in group 1 have the event, compared with 20 of 100 in group 0. Then\n\n\\[\\widehat{\\mathrm{OR}} =\\frac{40\\times80}{60\\times20} =\\frac83\\approx2.67.\\]\n\nThe probabilities are 0.40 and 0.20, so their probability ratio is 2, rather than 2.67."
    },
    {
      "heading": "Relationship to risk ratios",
      "text": "The risk ratio (RR), also called relative risk, compares event probabilities directly:\n\n\\[\\mathrm{RR}=\\frac{p_1}{p_0}.\\]\n\nThe definitions give the exact identity\n\n\\[\\mathrm{OR} =\\mathrm{RR}\\frac{1-p_0}{1-p_1}.\\]\n\nWhen both event probabilities are small, the final factor is close to 1, so the odds ratio approximates the risk ratio. This is the rare-outcome approximation. It concerns outcome frequencies in the relevant population groups, not merely the proportion of cases in a deliberately selected sample. For common outcomes, the difference can be substantial. (pubmed.ncbi.nlm.nih.gov)\n\nAn odds ratio alone does not determine an absolute probability change. If the baseline probability \\(p_0\\) is known, rearranging the definition gives\n\n\\[p_1=\\frac{\\mathrm{OR}\\,p_0} {1-p_0+\\mathrm{OR}\\,p_0}.\\]\n\nThus, the same odds ratio can correspond to different probability changes at different baseline probabilities."
    },
    {
      "heading": "Case–control studies",
      "text": "In a case–control study, participants are sampled according to outcome status, and their exposure histories are compared. Because investigators determine how many cases and controls enter the sample, sample outcome proportions generally do not estimate population risks directly. The exposure odds ratio can nevertheless estimate the population outcome odds ratio under appropriate sampling conditions, including exposure-independent sampling within outcome groups. (online.stat.psu.edu)\n\nThe population measure estimated also depends on how controls are selected. Sampling controls from people who remain non-cases estimates an outcome odds ratio; risk-set or incidence-density sampling can estimate an incidence rate ratio without requiring a rare outcome. These interpretations distinguish study-design properties from the mathematical definition of the odds ratio. (pmc.ncbi.nlm.nih.gov)"
    },
    {
      "heading": "Logistic regression",
      "text": "In logistic regression, the logit of the conditional probability of an event is modeled as\n\n\\[\\log\\!\\left(\\frac{p}{1-p}\\right) =\\beta_0+\\beta_1x_1+\\cdots+\\beta_kx_k.\\]\n\nWith other predictors held fixed, and without an interaction involving \\(x_j\\), a one-unit increase in \\(x_j\\) multiplies the odds by\n\n\\[e^{\\beta_j}.\\]\n\nFor a change of \\(\\Delta x_j\\), the corresponding odds ratio is \\(e^{\\beta_j\\Delta x_j}\\). An exponentiated coefficient therefore describes a conditional association, rather than a fixed change in probability. (online.stat.psu.edu)"
    },
    {
      "heading": "Statistical uncertainty",
      "text": "For sufficiently large independent samples with positive cell counts, an approximate standard error of the log sample odds ratio is\n\n\\[\\operatorname{SE}\\!\\left(\\log\\widehat{\\mathrm{OR}}\\right) \\approx \\sqrt{\\frac1a+\\frac1b+\\frac1c+\\frac1d}.\\]\n\nAn approximate 95% confidence interval is obtained by exponentiating the endpoints of\n\n\\[\\log\\widehat{\\mathrm{OR}} \\pm1.96\\, \\operatorname{SE}\\!\\left(\\log\\widehat{\\mathrm{OR}}\\right).\\]\n\nSparse tables and zero cells can make this approximation unreliable or undefined, requiring methods suited to small samples. Matched observations require analysis that accounts for their pairing, rather than automatic application of the independent-table formula. (online.stat.psu.edu)"
    },
    {
      "heading": "Adjustment and non-collapsibility",
      "text": "Odds ratios are generally non-collapsible: a population-wide, or marginal, odds ratio can differ from odds ratios conditional on another variable, even when that variable is not a confounder. Consequently, a difference between unadjusted and regression-adjusted odds ratios does not by itself establish confounding. Conditional and marginal odds ratios answer different statistical questions. (pmc.ncbi.nlm.nih.gov)\n\nLike other measures of association, an odds ratio does not by itself establish causation. Causal interpretation additionally depends on study design and assumptions about confounding, selection, and measurement. (cdc.gov)"
    }
  ],
  "links": [
    "statistics",
    "odds",
    "epidemiology",
    "probability",
    "contingency-table",
    "statistical-independence",
    "risk-ratio",
    "case-control-study",
    "logistic-regression",
    "logit",
    "conditional-probability",
    "standard-error",
    "confidence-interval",
    "confounding",
    "causation"
  ],
  "sources": [
    {
      "title": "Principles of Epidemiology: Lesson 3, Section 5",
      "url": "https://archive.cdc.gov/www_cdc_gov/csels/dsepd/ss1978/lesson3/section5.html"
    },
    {
      "title": "The relative merits of risk ratios and odds ratios",
      "url": "https://pubmed.ncbi.nlm.nih.gov/19414690/"
    },
    {
      "title": "Collapsibility in case-control studies",
      "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13221832/"
    },
    {
      "title": "Defining, Quantifying, and Interpreting “Noncollapsibility” in Epidemiologic Studies of Measures of “Effect”",
      "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC8530151/"
    },
    {
      "title": "Making apples from oranges: Comparing noncollapsible effect estimators and their standard errors after adjustment for different covariate sets",
      "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC7986756/"
    },
    {
      "title": "Analyzing and Interpreting Data",
      "url": "https://www.cdc.gov/field-epi-manual/php/chapters/analyze-interpret-data.html"
    }
  ],
  "license": "https://creativecommons.org/licenses/by/4.0/"
}