{
  "aliases": null,
  "backlinks": [
    {
      "field": "uses",
      "target": "3QB691PFPB"
    },
    {
      "field": "uses",
      "target": "HSTFKC0Y39"
    },
    {
      "field": "uses",
      "target": "NE0BW8Q2PX"
    },
    {
      "field": "uses",
      "target": "QQZPWDWS29"
    },
    {
      "field": "uses",
      "target": "RE02MP1H45"
    },
    {
      "field": "uses",
      "target": "Y3TX4J41TP"
    },
    {
      "field": "defines",
      "target": "Q0DXKAQXE1"
    }
  ],
  "body": "\n## Summary\n\nA parametric model is a [[statistical model|K3AMMSY8DD]] whose laws are described by finitely many real numbers, the parameters.\nInference in such a model reduces to learning a point of a subset of $\\R^k$.\nMost classical theory, such as maximum likelihood and the Cramér–Rao bound, is developed for parametric models.\n\n## Explanations\n\n### L1 human\n\nA parametric model is a family of distributions that you can tune with a few knobs.\nThe normal distributions form such a family: two knobs, the mean $\\mu$ and the variance $\\sigma^2$, fix the whole bell curve.\nLearning from data then means finding good settings of the knobs.\nA model with \"any distribution at all\" has no finite set of knobs, and it is called nonparametric.\n",
  "commit": "ff8a40749dc16545e3d2fc637f6b0196e81d0bfa",
  "front": {
    "kind": "concept",
    "msc": [
      "62A01",
      "62F99"
    ],
    "name": "Parametric model",
    "same_as": {
      "wikidata": "Q7135228",
      "wikipedia": "Parametric model"
    },
    "sources": [
      {
        "url": "https://en.wikipedia.org/wiki/Parametric_model"
      }
    ],
    "specializes": [
      "K3AMMSY8DD"
    ],
    "tag": "MSC0MR8VMH"
  },
  "kind": "concept",
  "link": "https://tamnd.github.io/math2/node/MSC0MR8VMH/",
  "links": [
    {
      "field": "specializes",
      "target": "K3AMMSY8DD"
    }
  ],
  "markdown": "https://tamnd.github.io/math2/node/MSC0MR8VMH.md",
  "msc": [
    "62A01",
    "62F99"
  ],
  "name": "Parametric model",
  "prov": null,
  "role": "",
  "source": "https://github.com/tamnd/math2/blob/main/nodes/MSC/MSC0MR8VMH.md",
  "status": null,
  "tag": "MSC0MR8VMH",
  "uri": "m2://MSC0MR8VMH",
  "url": "https://tamnd.github.io/math2/wiki/parametric-model/",
  "writing": {
    "tag": "MSC0MR8VMH",
    "kind": "concept",
    "level": "W0",
    "next": [
      {
        "what": "an inventory row",
        "note": "the row of the inventory that the node accounts for",
        "have": 0,
        "want": 1
      },
      {
        "what": "a source with a locator",
        "have": 0,
        "want": 1
      }
    ]
  }
}