{
  "name": "Score, Wald and likelihood ratio test calculation requirements",
  "description": "Original crosswalk compiling the fitted-model requirements and statistic inputs described by UCLA OARC and University of Minnesota likelihood notes, with implementation distinctions from the Minnesota and R documentation. The rows compare regular likelihood tests; asymptotic equivalence does not guarantee identical finite-sample results.",
  "page": "https://casrai.org/guides/score-test",
  "publisher": "CASRAI",
  "license": "https://creativecommons.org/licenses/by/4.0/",
  "dateModified": "2026-11-14T08:42:00Z",
  "temporalCoverage": null,
  "spatialCoverage": null,
  "columns": [
    {
      "name": "Test",
      "unit": "",
      "description": ""
    },
    {
      "name": "Maximum-likelihood fit required",
      "unit": "",
      "description": ""
    },
    {
      "name": "Statistic input",
      "unit": "",
      "description": ""
    },
    {
      "name": "Implementation distinction",
      "unit": "",
      "description": ""
    },
    {
      "name": "Sources",
      "unit": "",
      "description": ""
    }
  ],
  "rows": [
    {
      "Test": "Score (Rao / Lagrange multiplier)",
      "Maximum-likelihood fit required": "Restricted null model",
      "Statistic input": "Score vector and Fisher information evaluated at restricted estimates",
      "Implementation distinction": "The uncorrected one-proportion example corresponds to R prop.test with correct = FALSE.",
      "Sources": "https://www.stat.umn.edu/geyer/5421/notes/likelihood.html ; https://stat.ethz.ch/R-manual/R-patched/library/stats/html/prop.test.html"
    },
    {
      "Test": "Wald",
      "Maximum-likelihood fit required": "Unrestricted full model",
      "Statistic input": "Estimated departure from the restriction scaled by information at unrestricted estimates",
      "Implementation distinction": "R summary output for glm coefficients gives Wald tests.",
      "Sources": "https://www.stat.umn.edu/geyer/5421/notes/likelihood.html ; https://stats.oarc.ucla.edu/other/mult-pkg/faq/general/faqhow-are-the-likelihood-ratio-wald-and-lagrange-multiplier-score-tests-different-andor-similar/"
    },
    {
      "Test": "Likelihood ratio (Wilks)",
      "Maximum-likelihood fit required": "Restricted null model and unrestricted full model",
      "Statistic input": "Twice the difference of maximized log likelihoods",
      "Implementation distinction": "R glm analysis of deviance with a chi-square likelihood-ratio comparison uses both fits.",
      "Sources": "https://www.stat.umn.edu/geyer/5421/notes/likelihood.html ; https://stats.oarc.ucla.edu/other/mult-pkg/faq/general/faqhow-are-the-likelihood-ratio-wald-and-lagrange-multiplier-score-tests-different-andor-similar/"
    }
  ],
  "sources": [
    {
      "title": "UCLA OARC: likelihood ratio, Wald and Lagrange multiplier tests",
      "url": "https://stats.oarc.ucla.edu/other/mult-pkg/faq/general/faqhow-are-the-likelihood-ratio-wald-and-lagrange-multiplier-score-tests-different-andor-similar/",
      "accessed": "2026-11-14"
    },
    {
      "title": "Geyer: Likelihood Inference, sections 7.2 and 7.4",
      "url": "https://www.stat.umn.edu/geyer/5421/notes/likelihood.html",
      "accessed": "2026-11-14"
    },
    {
      "title": "R stats: prop.test",
      "url": "https://stat.ethz.ch/R-manual/R-patched/library/stats/html/prop.test.html",
      "accessed": "2026-11-14"
    }
  ]
}