{
  "aliases": null,
  "backlinks": [
    {
      "field": "uses",
      "target": "1JFKTEQVRX"
    },
    {
      "field": "uses",
      "target": "8085SD9EYY"
    },
    {
      "field": "uses",
      "target": "8DWRYNAMFT"
    },
    {
      "field": "uses",
      "target": "HSTFKC0Y39"
    },
    {
      "field": "uses",
      "target": "KV0F0E8YR2"
    },
    {
      "field": "uses",
      "target": "YMDADSX0E1"
    },
    {
      "field": "defines",
      "target": "8X7293647G"
    }
  ],
  "body": "\n## Summary\n\nThe score is the gradient of the log-likelihood with respect to the parameter.\nIt measures how sensitive the log-likelihood of the observed data is to small changes of the parameter.\nUnder regularity conditions its expectation at the true parameter is zero, and its covariance is the Fisher information.\nSetting the score equal to zero gives the likelihood equations, whose solutions are candidates for the maximum likelihood estimate.\n\n## Explanations\n\n### L1 human\n\nImagine the log-likelihood as a hill over the parameter axis.\nThe score is the slope of the hill at a given parameter value.\nAt the top of the hill, the maximum likelihood estimate, the slope is zero.\nFor one observation $x$ from a normal distribution with mean $\\mu$ and variance $1$, the score is $x - \\mu$: it is positive when the observation suggests a larger mean.\n",
  "commit": "ff8a40749dc16545e3d2fc637f6b0196e81d0bfa",
  "front": {
    "kind": "concept",
    "msc": [
      "62F10",
      "62B10"
    ],
    "name": "Score",
    "same_as": {
      "wikidata": "Q3952743",
      "wikipedia": "Informant function"
    },
    "sources": [
      {
        "url": "https://en.wikipedia.org/wiki/Informant_function"
      }
    ],
    "tag": "CP97GRVTQ0"
  },
  "kind": "concept",
  "link": "https://tamnd.github.io/math2/node/CP97GRVTQ0/",
  "links": null,
  "markdown": "https://tamnd.github.io/math2/node/CP97GRVTQ0.md",
  "msc": [
    "62F10",
    "62B10"
  ],
  "name": "Score",
  "prov": null,
  "role": "",
  "source": "https://github.com/tamnd/math2/blob/main/nodes/CP9/CP97GRVTQ0.md",
  "status": null,
  "tag": "CP97GRVTQ0",
  "uri": "m2://CP97GRVTQ0",
  "url": "https://tamnd.github.io/math2/wiki/score/",
  "writing": {
    "tag": "CP97GRVTQ0",
    "kind": "concept",
    "level": "W0",
    "next": [
      {
        "what": "a source with a locator",
        "have": 0,
        "want": 1
      }
    ]
  }
}
