Micron Document
<!DOCTYPE html>
<html class="client-nojs vector-feature-language-in-header-enabled vector-feature-language-in-main-page-header-disabled vector-feature-page-tools-pinned-disabled vector-feature-toc-pinned-clientpref-0 vector-toc-not-available vector-feature-main-menu-pinned-disabled vector-feature-limited-width-clientpref-1 vector-feature-limited-width-content-enabled vector-feature-custom-font-size-clientpref-1 vector-feature-appearance-pinned-clientpref-0 skin-theme-clientpref-day vector-sticky-header-enabled" lang="de" dir="ltr"><head>
<meta charset="UTF-8">
<title>Bootstrapping-Verfahren</title>
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<link rel="icon" type="image/png" href="./_res_/favicon.png">
<link rel="canonical" href="https://de.wikipedia.org/wiki/Bootstrapping-Verfahren"> <link href="./_mw_/ext.cite.styles.css" rel="stylesheet" type="text/css">
<link href="./_mw_/ext.math.styles.css" rel="stylesheet" type="text/css">
<link href="./_mw_/ext.wikimediamessages.styles.css" rel="stylesheet" type="text/css">
<link href="./_mw_/skins.vector.icons.css" rel="stylesheet" type="text/css">
<link href="./_mw_/skins.vector.search.codex.styles.css" rel="stylesheet" type="text/css">
<link href="./_mw_/skins.vector.styles.css" rel="stylesheet" type="text/css">
<meta name="ResourceLoaderDynamicStyles" content="">
<link href="./_mw_/ext.gadget.citeRef.css" rel="stylesheet" type="text/css">
<link href="./_mw_/ext.gadget.defaultPlainlinks.css" rel="stylesheet" type="text/css">
<link href="./_mw_/ext.gadget.dewikiCommonHide.css" rel="stylesheet" type="text/css">
<link href="./_mw_/ext.gadget.dewikiCommonLayout.css" rel="stylesheet" type="text/css">
<link href="./_mw_/ext.gadget.dewikiCommonStyle.css" rel="stylesheet" type="text/css">
<link href="./_mw_/ext.gadget.dewikiDarkmode.css" rel="stylesheet" type="text/css">
<link href="./_mw_/ext.gadget.dewikiResponsive.css" rel="stylesheet" type="text/css">
<link href="./_mw_/ext.gadget.specialSearch.css" rel="stylesheet" type="text/css">
<link rel="stylesheet" type="text/css" href="./_mw_/site.styles.css">
<link rel="stylesheet" type="text/css" href="./_mw_/noscript.css">
<link rel="stylesheet" type="text/css" href="./_res_/footer.css">
<link rel="stylesheet" type="text/css" href="./_res_/vector-2022.css">
</head>
<body class="skin--responsive skin-vector skin-vector-search-vue mediawiki ltr sitedir-ltr mw-hide-empty-elt ns-0 ns-subject page-Bootstrapping-Verfahren rootpage-Bootstrapping-Verfahren skin-vector-2022 action-view">
<div class="mw-page-container">
<div class="mw-page-container-inner">
<div class="mw-content-container">
<main id="content" class="mw-body">
<header class="mw-body-header vector-page-titlebar">
<h1 id="firstHeading" class="firstHeading mw-first-heading"><span class="mw-page-title-main">Bootstrapping-Verfahren</span></h1>
</header>
<a id="top"></a>
<div id="bodyContent" class="vector-body ve-init-mw-desktopArticleTarget-targetContainer" aria-labelledby="firstHeading" data-mw-ve-target-container="">
<div id="contentSub">
<div id="mw-content-subtitle"></div>
</div>
<div id="mw-content-text" class="mw-body-content mw-content-ltr" lang="de" dir="ltr"><div class="mw-content-ltr mw-parser-output" lang="de" dir="ltr"><p>Das <b>Bootstrapping-Verfahren</b> oder <b>Bootstrap-Verfahren</b> (selten: <b>Münchhausenmethode</b>) ist in der <a href="Statistik" title="Statistik">Statistik</a> eine Methode des <a href="Resampling" title="Resampling">Resampling</a>.
</p><p>Beim Bootstrapping-Verfahren ist die Grundannahme, dass die vorliegende <a href="Zufallsstichprobe" title="Zufallsstichprobe">Zufallsstichprobe</a> „<a href="Repr%C3%A4sentativit%C3%A4t" title="Repräsentativität">repräsentativ</a>“ für die <a href="Grundgesamtheit" title="Grundgesamtheit">Grundgesamtheit</a> ist, aus der sie gezogen wurde. Konzeptionell wird nun diese Grundgesamtheit durch die Stichprobe ersetzt. Durch wiederholtes <a href="Urnenmodell" title="Urnenmodell">Ziehen mit Zurücklegen</a> werden neue unabhängige Stichproben (die Stichprobenwiederholungen) erzeugt, auf deren Grundlage dann Statistiken sowie deren Verteilungen berechnet werden können.
</p><p>Verwendung finden Bootstrap-Methoden, wenn die theoretische Verteilung der interessierenden Statistik nicht bekannt ist. Die Methode wurde erstmals von <a href="Bradley_Efron" title="Bradley Efron">Bradley Efron</a> 1979 beschrieben<sup id="cite_ref-1" class="reference"><a href="#cite_note-1"><span class="cite-bracket">[</span>1<span class="cite-bracket">]</span></a></sup> und geht aus Überlegungen zur Verbesserung der <a href="Jackknife-Methode" title="Jackknife-Methode">Jackknife-Methode</a> hervor<sup id="cite_ref-Efron_2003_2-0" class="reference"><a href="#cite_note-Efron_2003-2"><span class="cite-bracket">[</span>2<span class="cite-bracket">]</span></a></sup>.
</p><p>Der Bootstrap ersetzt in der Regel die theoretische Verteilungsfunktion <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle F}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>F</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle F}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/545fd099af8541605f7ee55f08225526be88ce57.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.338ex; width:1.741ex; height:2.176ex;" alt="{\displaystyle F}" loading="lazy"></span> einer <a href="Zufallsvariable" title="Zufallsvariable">Zufallsvariablen</a> durch die <a href="Empirische_Verteilungsfunktion" title="Empirische Verteilungsfunktion">empirische Verteilungsfunktion</a> <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle F_{n}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msub>
<mi>F</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>n</mi>
</mrow>
</msub>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle F_{n}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/76cdf519c21deec43f984815e57e15d2dd3575d7.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.671ex; width:2.713ex; height:2.509ex;" alt="{\displaystyle F_{n}}" loading="lazy"></span> der Stichprobe <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle x_{1},\ldots ,x_{n}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msub>
<mi>x</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>1</mn>
</mrow>
</msub>
<mo>,</mo>
<mo>…<!-- … --></mo>
<mo>,</mo>
<msub>
<mi>x</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>n</mi>
</mrow>
</msub>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle x_{1},\ldots ,x_{n}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/737e02a5fbf8bc31d443c91025339f9fd1de1065.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.671ex; width:10.11ex; height:2.009ex;" alt="{\displaystyle x_{1},\ldots ,x_{n}}" loading="lazy"></span>. Es ist daher offensichtlich, dass Bootstrapping nur dann gut funktioniert, wenn die empirische Verteilungsfunktion die tatsächliche Verteilungsfunktion hinreichend gut approximieren kann, was eine gewisse Größe der ursprünglichen Stichprobe voraussetzt (vergleiche Konvergenzeigenschaften der empirischen Verteilungsfunktion).
</p><p>Bootstrapping kann als <a href="Monte-Carlo-Methode" class="mw-redirect" title="Monte-Carlo-Methode">Monte-Carlo-Methode</a> verstanden werden, da es wiederholt <a href="Zufallsstichprobe" title="Zufallsstichprobe">zufällige Stichproben</a> einer Verteilung zieht.<sup id="cite_ref-3" class="reference"><a href="#cite_note-3"><span class="cite-bracket">[</span>3<span class="cite-bracket">]</span></a></sup>
</p><p><a href="Nichtparametrische_Statistik" title="Nichtparametrische Statistik">Nichtparametrisches</a> Bootstrapping ermöglicht weitestgehend ohne oder mit wenigen Modellannahmen, zuverlässig Verteilungen von Statistiken zu schätzen. Es ist unzuverlässig, falls die zugrundeliegende Verteilung <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle F}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>F</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle F}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/545fd099af8541605f7ee55f08225526be88ce57.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.338ex; width:1.741ex; height:2.176ex;" alt="{\displaystyle F}" loading="lazy"></span> unendliche Varianz besitzt<sup id="cite_ref-4" class="reference"><a href="#cite_note-4"><span class="cite-bracket">[</span>4<span class="cite-bracket">]</span></a></sup>.
</p><p>Die Bezeichnung „Bootstrapping“ geht zurück auf die englische <a href="Redewendung" title="Redewendung">Redewendung</a>: „To pull oneself up by one's bootstraps“ (dt. wörtlich: <i>sich an den eigenen Stiefelriemen hochziehen</i>). Dies spielt darauf an, dass beim Bootstrapping-Verfahren aus einer Stichprobe erneut Stichproben gezogen werden. <a href="Hieronymus_Carl_Friedrich_von_M%C3%BCnchhausen" title="Hieronymus Carl Friedrich von Münchhausen">Baron Münchhausen</a> erklärte bekanntlich, sich an den eigenen Haaren aus einem Sumpf gezogen zu haben. Daher der Name „Münchhausenmethode“.<sup id="cite_ref-5" class="reference"><a href="#cite_note-5"><span class="cite-bracket">[</span>5<span class="cite-bracket">]</span></a></sup>
</p><p>Bootstrapping kann intuitiv als Beobachtung der Realisierungen in <a href="Parallelwelt" title="Parallelwelt">Parallelwelten</a> (der Bootstrap-Welt) verstanden werden<sup id="cite_ref-6" class="reference"><a href="#cite_note-6"><span class="cite-bracket">[</span>6<span class="cite-bracket">]</span></a></sup>.
</p>

<div class="mw-heading mw-heading2"><h2 id="Anwendungen">Anwendungen</h2></div>
<p>Bootstrapping als zufälliges wiederholtes Ziehen kann auf eine Vielzahl von Grundgesamtheiten angewendet werden. Voraussetzung ist nur, dass die Daten (zeit-)unabhängig verwendet werden können. Wenn man bspw. aus einer Reihe von 60 historischen aufeinander folgender Monatsrenditen <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle r_{j}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msub>
<mi>r</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>j</mi>
</mrow>
</msub>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle r_{j}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/a7d3b724fc249d56f0d550b92f6891380467e350.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -1.005ex; width:1.958ex; height:2.343ex;" alt="{\displaystyle r_{j}}" loading="lazy"></span> 12 einzelne Monatsrenditen zufällig zieht und die Wachstumsfaktoren <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle (1+r_{j})}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mo stretchy="false">(</mo>
<mn>1</mn>
<mo>+</mo>
<msub>
<mi>r</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>j</mi>
</mrow>
</msub>
<mo stretchy="false">)</mo>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle (1+r_{j})}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/ce9b576084bedd173b76be16c20266f1ba5031b8.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -1.005ex; width:7.771ex; height:3.009ex;" alt="{\displaystyle (1+r_{j})}" loading="lazy"></span> zu Jahresrenditen multipliziert und diesen Vorgang wie beim <a href="Monte-Carlo-Verfahren" class="mw-redirect" title="Monte-Carlo-Verfahren">Monte-Carlo-Verfahren</a> sehr häufig wiederholt, so erhält man dadurch eine Verteilungsfunktion der (erwarteten) Jahresrenditen, die man statistisch auswerten kann<sup id="cite_ref-7" class="reference"><a href="#cite_note-7"><span class="cite-bracket">[</span>7<span class="cite-bracket">]</span></a></sup>.
</p><p>Das Verfahren eignet sich einerseits für deskriptive Kennzahlen wie das arithmetische Mittel oder den Median, aber auch für komplexere Methoden der Inferenzstatistik wie <a href="Regressionsanalyse" title="Regressionsanalyse">Regressionsmodelle</a>. Durch die Flexibilität des Verfahrens ist es möglich, <a href="Standardfehler" title="Standardfehler">Standardfehler</a> beliebiger Statistiken zu generieren und somit Inferenzen zu erleichtern.
</p>
<ul><li>Bootstrap-Konfidenzbereiche, Bootstrap-Konfidenzintervalle sind jedoch auch mit Unsicherheiten behaftet, vergleiche <a href="Empirisches_Quantil" title="Empirisches Quantil">Empirisches Quantil</a></li>
<li>Bootstrap-Tests<sup id="cite_ref-8" class="reference"><a href="#cite_note-8"><span class="cite-bracket">[</span>8<span class="cite-bracket">]</span></a></sup></li>
<li><a href="Bootstrap_aggregating" title="Bootstrap aggregating">Bootstrap aggregating</a></li></ul>
<div class="mw-heading mw-heading2"><h2 id="Verfahren">Verfahren</h2></div>
<p>Es gibt viele Bootstrap-Verfahren, unter anderem Bayesian Bootstrap, Smooth Bootstrap, Parametric Bootstrap, Residual Bootstrap, Gaussian process regression Bootstrap, Wild Bootstrap, Block Bootstrap.
</p>
<div class="mw-heading mw-heading3"><h3 id="i.i.d._Bootstrap">i.i.d. Bootstrap</h3></div>


<p>Gegeben sei eine Stichprobe <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle x_{1},\dots ,x_{n}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msub>
<mi>x</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>1</mn>
</mrow>
</msub>
<mo>,</mo>
<mo>…<!-- … --></mo>
<mo>,</mo>
<msub>
<mi>x</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>n</mi>
</mrow>
</msub>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle x_{1},\dots ,x_{n}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/e5afdbc2d248d8fa9ba2c4f5188d946a0537e753.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.671ex; width:10.11ex; height:2.009ex;" alt="{\displaystyle x_{1},\dots ,x_{n}}" loading="lazy"></span>, die wir als Realisierung von <a href="Unabh%C3%A4ngig_und_identisch_verteilte_Zufallsvariablen" title="Unabhängig und identisch verteilte Zufallsvariablen">unabhängig und identisch verteilten</a> (i. i. d.) Zufallsvariablen <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle X_{1},\dots ,X_{n}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msub>
<mi>X</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>1</mn>
</mrow>
</msub>
<mo>,</mo>
<mo>…<!-- … --></mo>
<mo>,</mo>
<msub>
<mi>X</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>n</mi>
</mrow>
</msub>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle X_{1},\dots ,X_{n}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/38ed92ce88f900210607bbb8f4d66e14d52d7a17.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.671ex; width:11.299ex; height:2.509ex;" alt="{\displaystyle X_{1},\dots ,X_{n}}" loading="lazy"></span> mit unbekannter Verteilungsfunktion <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle F}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>F</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle F}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/545fd099af8541605f7ee55f08225526be88ce57.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.338ex; width:1.741ex; height:2.176ex;" alt="{\displaystyle F}" loading="lazy"></span> verstehen. Nun werden im einfachsten Fall <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle B}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>B</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle B}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/47136aad860d145f75f3eed3022df827cee94d7a.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.338ex; width:1.764ex; height:2.176ex;" alt="{\displaystyle B}" loading="lazy"></span> Bootstrap-<a href="Stichprobenwiederholung" class="mw-redirect" title="Stichprobenwiederholung">Stichprobenwiederholungen</a> <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle x_{b}=(x_{1}^{*},\ldots ,x_{n}^{*})\,,b=1,\ldots ,B}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msub>
<mi>x</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>b</mi>
</mrow>
</msub>
<mo>=</mo>
<mo stretchy="false">(</mo>
<msubsup>
<mi>x</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>1</mn>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mo>∗<!-- ∗ --></mo>
</mrow>
</msubsup>
<mo>,</mo>
<mo>…<!-- … --></mo>
<mo>,</mo>
<msubsup>
<mi>x</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>n</mi>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mo>∗<!-- ∗ --></mo>
</mrow>
</msubsup>
<mo stretchy="false">)</mo>
<mspace width="thinmathspace"></mspace>
<mo>,</mo>
<mi>b</mi>
<mo>=</mo>
<mn>1</mn>
<mo>,</mo>
<mo>…<!-- … --></mo>
<mo>,</mo>
<mi>B</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle x_{b}=(x_{1}^{*},\ldots ,x_{n}^{*})\,,b=1,\ldots ,B}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/bb1020a7e8bfa69294f2cbb9169d25bb4486d83f.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -1.005ex; width:30.907ex; height:3.009ex;" alt="{\displaystyle x_{b}=(x_{1}^{*},\ldots ,x_{n}^{*})\,,b=1,\ldots ,B}" loading="lazy"></span> generiert, indem je Ziehung <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle n}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>n</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle n}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/a601995d55609f2d9f5e233e36fbe9ea26011b3b.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.338ex; width:1.395ex; height:1.676ex;" alt="{\displaystyle n}" loading="lazy"></span> mal aus der gegebenen Stichprobe ein Wert mit Zurücklegen gezogen wird.
Dieses Vorgehen entspricht dem wiederholten Ziehen von Zufallszahlen aus der <a href="Empirische_Verteilungsfunktion" title="Empirische Verteilungsfunktion">empirischen Verteilungsfunktion</a> <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle {\hat {F}}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mrow class="MJX-TeXAtom-ORD">
<mrow class="MJX-TeXAtom-ORD">
<mover>
<mi>F</mi>
<mo stretchy="false">^<!-- ^ --></mo>
</mover>
</mrow>
</mrow>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle {\hat {F}}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/e22e0749dfc79fd15d8f156203a276fb7092fc51.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.338ex; width:1.805ex; height:2.843ex;" alt="{\displaystyle {\hat {F}}}" loading="lazy"></span>.
Für jede Bootstrap-Stichprobe wird der Wert <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle T_{b}(x_{1}^{*},\ldots ,x_{n}^{*})=T(x_{b})}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msub>
<mi>T</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>b</mi>
</mrow>
</msub>
<mo stretchy="false">(</mo>
<msubsup>
<mi>x</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>1</mn>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mo>∗<!-- ∗ --></mo>
</mrow>
</msubsup>
<mo>,</mo>
<mo>…<!-- … --></mo>
<mo>,</mo>
<msubsup>
<mi>x</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>n</mi>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mo>∗<!-- ∗ --></mo>
</mrow>
</msubsup>
<mo stretchy="false">)</mo>
<mo>=</mo>
<mi>T</mi>
<mo stretchy="false">(</mo>
<msub>
<mi>x</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>b</mi>
</mrow>
</msub>
<mo stretchy="false">)</mo>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle T_{b}(x_{1}^{*},\ldots ,x_{n}^{*})=T(x_{b})}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/3cb3beb74fe7c726646b4c14b83cafc1f40acd0d.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -1.005ex; width:23.026ex; height:3.009ex;" alt="{\displaystyle T_{b}(x_{1}^{*},\ldots ,x_{n}^{*})=T(x_{b})}" loading="lazy"></span> der interessierenden Statistik <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle T}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>T</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle T}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/ec7200acd984a1d3a3d7dc455e262fbe54f7f6e0.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.338ex; width:1.636ex; height:2.176ex;" alt="{\displaystyle T}" loading="lazy"></span> berechnet.
Die Verteilung von <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle T(X_{1},\ldots ,X_{n})}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>T</mi>
<mo stretchy="false">(</mo>
<msub>
<mi>X</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>1</mn>
</mrow>
</msub>
<mo>,</mo>
<mo>…<!-- … --></mo>
<mo>,</mo>
<msub>
<mi>X</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>n</mi>
</mrow>
</msub>
<mo stretchy="false">)</mo>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle T(X_{1},\ldots ,X_{n})}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/211724ade18dc41a92126fd6d49b013457ce1824.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.838ex; width:14.745ex; height:2.843ex;" alt="{\displaystyle T(X_{1},\ldots ,X_{n})}" loading="lazy"></span> wird schließlich durch die empirische Verteilung der <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle B}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>B</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle B}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/47136aad860d145f75f3eed3022df827cee94d7a.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.338ex; width:1.764ex; height:2.176ex;" alt="{\displaystyle B}" loading="lazy"></span> Werte <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle T_{b}(x_{1}^{*},\ldots ,x_{n}^{*})}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msub>
<mi>T</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>b</mi>
</mrow>
</msub>
<mo stretchy="false">(</mo>
<msubsup>
<mi>x</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>1</mn>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mo>∗<!-- ∗ --></mo>
</mrow>
</msubsup>
<mo>,</mo>
<mo>…<!-- … --></mo>
<mo>,</mo>
<msubsup>
<mi>x</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>n</mi>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mo>∗<!-- ∗ --></mo>
</mrow>
</msubsup>
<mo stretchy="false">)</mo>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle T_{b}(x_{1}^{*},\ldots ,x_{n}^{*})}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/49b6338fce915f36d1cef582f97f18185f5e19b1.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -1.005ex; width:14.215ex; height:3.009ex;" alt="{\displaystyle T_{b}(x_{1}^{*},\ldots ,x_{n}^{*})}" loading="lazy"></span> approximiert. Aus dieser Verteilung der Statistik T kann direkt ein <a href="Konfidenzintervall" title="Konfidenzintervall">Konfidenzintervall</a> mithilfe der <a href="Inverse_Verteilungsfunktion" class="mw-redirect" title="Inverse Verteilungsfunktion">inversen Verteilungsfunktion</a> erzeugt werden.<sup id="cite_ref-Efron_2003_2-1" class="reference"><a href="#cite_note-Efron_2003-2"><span class="cite-bracket">[</span>2<span class="cite-bracket">]</span></a></sup> Zudem lassen sich Erwartungswert und Varianz durch den Stichprobenmittelwert und Stichprobenvarianz schätzen.
</p><p>Die Zahl der möglichen unterschiedlichen Stichprobenwiederholungen (bei Beachtung der Reihenfolge<sup id="cite_ref-9" class="reference"><a href="#cite_note-9"><span class="cite-bracket">[</span>9<span class="cite-bracket">]</span></a></sup>) beim Ziehen mit Zurücklegen ist <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle \underbrace {n\cdot n\dots n} _{\text{n mal}}=n^{n}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<munder>
<mrow class="MJX-TeXAtom-OP MJX-fixedlimits">
<munder>
<mrow>
<mi>n</mi>
<mo>⋅<!-- ⋅ --></mo>
<mi>n</mi>
<mo>…<!-- … --></mo>
<mi>n</mi>
</mrow>
<mo>⏟<!-- ⏟ --></mo>
</munder>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mtext>n mal</mtext>
</mrow>
</munder>
<mo>=</mo>
<msup>
<mi>n</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>n</mi>
</mrow>
</msup>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle \underbrace {n\cdot n\dots n} _{\text{n mal}}=n^{n}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/7a92d19d2a68505bd6d788fa61b00d1d692115e6.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -3.838ex; width:15.072ex; height:5.843ex;" alt="{\displaystyle \underbrace {n\cdot n\dots n} _{\text{n mal}}=n^{n}}" loading="lazy"></span> und steigt somit sehr schnell mit zunehmender Stichprobengröße <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle n}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>n</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle n}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/a601995d55609f2d9f5e233e36fbe9ea26011b3b.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.338ex; width:1.395ex; height:1.676ex;" alt="{\displaystyle n}" loading="lazy"></span>. Daher beschränkt man sich typischerweise auf eine <a href="Monte-Carlo-Simulation" title="Monte-Carlo-Simulation">Monte-Carlo-Simulation</a>, welche eine bestimmte Zahl zufälliger Stichprobenwiederholungen zieht.
</p>
<div class="mw-heading mw-heading3"><h3 id="Block-Bootstrap">Block-Bootstrap</h3></div>
<p>Block-Bootstrap<sup id="cite_ref-10" class="reference"><a href="#cite_note-10"><span class="cite-bracket">[</span>10<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-11" class="reference"><a href="#cite_note-11"><span class="cite-bracket">[</span>11<span class="cite-bracket">]</span></a></sup> wird bei zeitlich korrelierten Daten eingesetzt, da <a href="Unabh%C3%A4ngig_und_identisch_verteilte_Zufallsvariablen" title="Unabhängig und identisch verteilte Zufallsvariablen">i.i.d</a> Bootstrap die zeitliche <a href="Korrelation" title="Korrelation">Korrelation</a> zerstören würde.
Beim Block-Bootstrap werden die Daten zunächst in überlappende oder nichtüberlappende, zusammenhängende, Blöcke eingeteilt. Das Signal wird dann z.&nbsp;B. durch <a href="Ausgleichungsrechnung" title="Ausgleichungsrechnung">Anpassung</a> einer Modellfunktion in einen Trend- und einen Residualanteil aufgeteilt. Nun werden so viele Residualblöcke durch <a href="Ziehen_mit_Zur%C3%BCcklegen" class="mw-redirect" title="Ziehen mit Zurücklegen">Zurücklegen</a> gezogen und aneinander angehängt, bis die ursprüngliche Länge des Signals erreicht ist. Diese gezogenen Residuuen werden auf die Trendzeitreihe addiert und so wird eine <a href="Stichprobenwiederholung" class="mw-redirect" title="Stichprobenwiederholung">Stichprobenwiederholung</a> erhalten. Dieser Vorgang wird nun oft (z.&nbsp;B. <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle B=100\dots 1000}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>B</mi>
<mo>=</mo>
<mn>100</mn>
<mo>…<!-- … --></mo>
<mn>1000</mn>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle B=100\dots 1000}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/b06a23d46fa8e609a53555db7b4a6763ed60aac0.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.338ex; width:16.497ex; height:2.176ex;" alt="{\displaystyle B=100\dots 1000}" loading="lazy"></span>) wiederholt. Dann kann auf diesen Stichprobenwiederholungen die gewünschte <a href="Statistik_(Funktion)" title="Statistik (Funktion)">Statistik (Funktion)</a> berechnet werden.
</p>
<div class="mw-heading mw-heading3"><h3 id="Parametrisches_Bootstrap">Parametrisches Bootstrap</h3></div>
<p>Beim <a href="Parametrische_Statistik" title="Parametrische Statistik">parametrischen</a> Bootstrap wird angenommen, dass die originale Stichprobe einer bekannten Verteilung mit Parametern <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle \theta }">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>θ<!-- θ --></mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle \theta }</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/6e5ab2664b422d53eb0c7df3b87e1360d75ad9af.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.338ex; width:1.09ex; height:2.176ex;" alt="{\displaystyle \theta }" loading="lazy"></span> folgt. Diese Parameter werden zum Beispiel mithilfe der <a href="Maximum-Likelihood-Methode" title="Maximum-Likelihood-Methode">Maximum-Likelihood-Methode</a> geschätzt, sodass man den Schätzwert <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle {\hat {\theta }}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mrow class="MJX-TeXAtom-ORD">
<mrow class="MJX-TeXAtom-ORD">
<mover>
<mi>θ<!-- θ --></mi>
<mo stretchy="false">^<!-- ^ --></mo>
</mover>
</mrow>
</mrow>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle {\hat {\theta }}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/f0eaae56d74c5844e86caeed8ae205ff9e413bba.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.338ex; width:1.356ex; height:2.843ex;" alt="{\displaystyle {\hat {\theta }}}" loading="lazy"></span> erhält. Die geschätzte <a href="Verteilungsfunktion" title="Verteilungsfunktion">Verteilungsfunktion</a> ist <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle {\hat {F}}=F_{\hat {\theta }}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mrow class="MJX-TeXAtom-ORD">
<mrow class="MJX-TeXAtom-ORD">
<mover>
<mi>F</mi>
<mo stretchy="false">^<!-- ^ --></mo>
</mover>
</mrow>
</mrow>
<mo>=</mo>
<msub>
<mi>F</mi>
<mrow class="MJX-TeXAtom-ORD">
<mrow class="MJX-TeXAtom-ORD">
<mover>
<mi>θ<!-- θ --></mi>
<mo stretchy="false">^<!-- ^ --></mo>
</mover>
</mrow>
</mrow>
</msub>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle {\hat {F}}=F_{\hat {\theta }}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/9531f5db566d2e84111d327c4512e804fc0eadd9.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -1.171ex; width:7.646ex; height:3.676ex;" alt="{\displaystyle {\hat {F}}=F_{\hat {\theta }}}" loading="lazy"></span> und aus dieser Verteilung werden wie beim nichtparametrischen Bootstrap wiederholt Stichproben gezogen.
</p>
<div class="mw-heading mw-heading3"><h3 id="m-out-of-n_Bootstrap">m-out-of-n Bootstrap</h3></div>
<p>Bei dieser Version des Bootstrap werden kleinere Stichprobenwiederholungen gezogen<sup id="cite_ref-12" class="reference"><a href="#cite_note-12"><span class="cite-bracket">[</span>12<span class="cite-bracket">]</span></a></sup><sup id="cite_ref-13" class="reference"><a href="#cite_note-13"><span class="cite-bracket">[</span>13<span class="cite-bracket">]</span></a></sup>, dies ist beispielsweise beim bootstrapping von Extremwerten notwendig.
</p>
<div class="mw-heading mw-heading2"><h2 id="Bootstrap-Stichprobenverteilungen">Bootstrap-Stichprobenverteilungen</h2></div>

<p>Wenn eine hinreichend große Stichprobe repräsentativ für die Grundgesamtheit ist, kann die <a href="Stichprobenverteilung" title="Stichprobenverteilung">Stichprobenverteilung</a> für eine beliebige <a href="Stichprobenfunktion" title="Stichprobenfunktion">Stichprobenfunktion</a> nichtparametrisch mit Hilfe des Bootstrap-Verfahrens geschätzt werden, <i>ohne</i> dass die Verteilung der <a href="Stichprobenvariable" class="mw-redirect" title="Stichprobenvariable">Stichprobenvariablen</a> <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle X_{i}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msub>
<mi>X</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>i</mi>
</mrow>
</msub>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle X_{i}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/af4a0955af42beb5f85aa05fb8c07abedc13990d.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.671ex; width:2.724ex; height:2.509ex;" alt="{\displaystyle X_{i}}" loading="lazy"></span> bekannt sein muss.
</p>
<div class="mw-heading mw-heading2"><h2 id="Beispiel">Beispiel</h2></div>
<p><a href="Bradley_Efron" title="Bradley Efron">Efron</a> und Tibshirani<sup id="cite_ref-14" class="reference"><a href="#cite_note-14"><span class="cite-bracket">[</span>14<span class="cite-bracket">]</span></a></sup> geben folgendes Beispiel für den parametrischen Bootstrap: Die Titelseite der <a href="The_New_York_Times" title="The New York Times">New York Times</a> vom 27. Januar 1987 berichtete von einer Studie, nach der das Risiko für einen <a href="Herzinfarkt" title="Herzinfarkt">Herzinfarkt</a> durch die regelmäßige Einnahme kleiner Dosen <a href="Aspirin_(Marke)" title="Aspirin (Marke)">Aspirin</a> reduziert würde. Folgende Daten wurden erhoben:
</p>
<table class="wikitable">
<caption>
</caption>
<tbody><tr>
<th>
</th>
<th>Herzinfarkt
<p><small>(tödlich und nicht tödlich)</small>
</p>
</th>
<th>Probanden
</th></tr>
<tr>
<td>Aspirin-Gruppe
</td>
<td>104
</td>
<td>11037
</td></tr>
<tr>
<td>Placebo-Gruppe
</td>
<td>189
</td>
<td>11034
</td></tr></tbody></table>
<p>Für die Herzinfarktraten beider Gruppen ergibt sich <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle 104/11037<189/11034}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mn>104</mn>
<mrow class="MJX-TeXAtom-ORD">
<mo>/</mo>
</mrow>
<mn>11037</mn>
<mo>&lt;</mo>
<mn>189</mn>
<mrow class="MJX-TeXAtom-ORD">
<mo>/</mo>
</mrow>
<mn>11034</mn>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle 104/11037&lt;189/11034}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/fa359402193afb5e391d8ad32c168fc3487f5da2.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.838ex; width:24.023ex; height:2.843ex;" alt="{\displaystyle 104/11037<189/11034}" loading="lazy"></span>. Der Quotient der Raten beträgt <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle {\frac {104/11037}{189/11034}}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mrow class="MJX-TeXAtom-ORD">
<mfrac>
<mrow>
<mn>104</mn>
<mrow class="MJX-TeXAtom-ORD">
<mo>/</mo>
</mrow>
<mn>11037</mn>
</mrow>
<mrow>
<mn>189</mn>
<mrow class="MJX-TeXAtom-ORD">
<mo>/</mo>
</mrow>
<mn>11034</mn>
</mrow>
</mfrac>
</mrow>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle {\frac {104/11037}{189/11034}}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/7ada91ff3466207766e0d967a94f5e62f854f559.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -2.671ex; width:11.298ex; height:6.509ex;" alt="{\displaystyle {\frac {104/11037}{189/11034}}}" loading="lazy"></span>. Diese Zahl ist <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle <1}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mo>&lt;</mo>
<mn>1</mn>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle &lt;1}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/108cec02cce68d5f12865ff93be5e54f3c2924d7.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.338ex; width:3.616ex; height:2.176ex;" alt="{\displaystyle <1}" loading="lazy"></span>, sodass <i>diese</i> Daten tatsächlich suggerieren, dass die Einnahme von Aspirin das Herzinfarktsrisiko reduziert. Ist diese Erhebung <a href="Statistische_Signifikanz" title="Statistische Signifikanz">statistisch signifikant</a> und kann auf die Grundgesamtheit übertragen werden oder können diese Ergebnisse durch zufällige Einflüsse erklärt werden? Eine Möglichkeit, dies zu prüfen, bietet der <a href="Exakter_Test_nach_Fisher" title="Exakter Test nach Fisher">exakte Test nach Fisher</a>. Eine andere Möglichkeit bietet das Bootstrapping-Verfahren. Bezeichne mit <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle p}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>p</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle p}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/81eac1e205430d1f40810df36a0edffdc367af36.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.671ex; margin-left: -0.089ex; width:1.259ex; height:2.009ex;" alt="{\displaystyle p}" loading="lazy"></span> bzw. <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle q}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>q</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle q}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/06809d64fa7c817ffc7e323f85997f783dbdf71d.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.671ex; width:1.07ex; height:2.009ex;" alt="{\displaystyle q}" loading="lazy"></span> die Wahrscheinlichkeit, dass eine Person der Aspiringruppe bzw. Placebo-Gruppe innerhalb des Studienzeitraums einen Herzinfarkt erleidet. Ziel ist es nun, ein approximatives Bootstrap-Konfidenzintervall für <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle p/q}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>p</mi>
<mrow class="MJX-TeXAtom-ORD">
<mo>/</mo>
</mrow>
<mi>q</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle p/q}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/8fa5bd4cf049744deac0ac4a04c07998bd6befa9.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.838ex; margin-left: -0.089ex; width:3.491ex; height:2.843ex;" alt="{\displaystyle p/q}" loading="lazy"></span> zu konstruieren.
</p><p>Wähle <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle X\sim \operatorname {Bin} (11037,p)}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>X</mi>
<mo>∼<!-- ∼ --></mo>
<mi>Bin</mi>
<mo>⁡<!-- ⁡ --></mo>
<mo stretchy="false">(</mo>
<mn>11037</mn>
<mo>,</mo>
<mi>p</mi>
<mo stretchy="false">)</mo>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle X\sim \operatorname {Bin} (11037,p)}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/de3f75c457e9daac82fe98b747af2c42ae53ea55.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.838ex; width:18.488ex; height:2.843ex;" alt="{\displaystyle X\sim \operatorname {Bin} (11037,p)}" loading="lazy"></span> und <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle Y\sim \operatorname {Bin} (11034,q)}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>Y</mi>
<mo>∼<!-- ∼ --></mo>
<mi>Bin</mi>
<mo>⁡<!-- ⁡ --></mo>
<mo stretchy="false">(</mo>
<mn>11034</mn>
<mo>,</mo>
<mi>q</mi>
<mo stretchy="false">)</mo>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle Y\sim \operatorname {Bin} (11034,q)}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/ebd266ab433c5562fe2daa109350db0bd1b086fc.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.838ex; width:18.182ex; height:2.843ex;" alt="{\displaystyle Y\sim \operatorname {Bin} (11034,q)}" loading="lazy"></span>. In der Studie wurde die Realisierung <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle (x,y)=(104,189)}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mo stretchy="false">(</mo>
<mi>x</mi>
<mo>,</mo>
<mi>y</mi>
<mo stretchy="false">)</mo>
<mo>=</mo>
<mo stretchy="false">(</mo>
<mn>104</mn>
<mo>,</mo>
<mn>189</mn>
<mo stretchy="false">)</mo>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle (x,y)=(104,189)}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/81893d811a041f5853f46bdd63d9a439286fb437.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.838ex; width:18.245ex; height:2.843ex;" alt="{\displaystyle (x,y)=(104,189)}" loading="lazy"></span> beobachtet. Ein <a href="Sch%C3%A4tzfunktion" title="Schätzfunktion">Schätzer</a> für <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle p/q}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>p</mi>
<mrow class="MJX-TeXAtom-ORD">
<mo>/</mo>
</mrow>
<mi>q</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle p/q}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/8fa5bd4cf049744deac0ac4a04c07998bd6befa9.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.838ex; margin-left: -0.089ex; width:3.491ex; height:2.843ex;" alt="{\displaystyle p/q}" loading="lazy"></span> ist gegeben durch <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle T={\frac {X/11037}{Y/11034}}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>T</mi>
<mo>=</mo>
<mrow class="MJX-TeXAtom-ORD">
<mfrac>
<mrow>
<mi>X</mi>
<mrow class="MJX-TeXAtom-ORD">
<mo>/</mo>
</mrow>
<mn>11037</mn>
</mrow>
<mrow>
<mi>Y</mi>
<mrow class="MJX-TeXAtom-ORD">
<mo>/</mo>
</mrow>
<mn>11034</mn>
</mrow>
</mfrac>
</mrow>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle T={\frac {X/11037}{Y/11034}}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/20ef040706572f19086ad0010aee83122444b9fc.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -2.671ex; width:14.526ex; height:6.509ex;" alt="{\displaystyle T={\frac {X/11037}{Y/11034}}}" loading="lazy"></span>. In der o.&nbsp;g. Studie wurde die Realisierung <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle 0{,}55}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mn>0</mn>
<mrow class="MJX-TeXAtom-ORD">
<mo>,</mo>
</mrow>
<mn>55</mn>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle 0{,}55}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/111b0a696d47c706e8a7411105760e623b717db5.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.671ex; width:4.134ex; height:2.509ex;" alt="{\displaystyle 0{,}55}" loading="lazy"></span> beobachtet. Um weitere Realisierungen für <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle T}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>T</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle T}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/ec7200acd984a1d3a3d7dc455e262fbe54f7f6e0.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.338ex; width:1.636ex; height:2.176ex;" alt="{\displaystyle T}" loading="lazy"></span> zu generieren, benötigt man weitere Realisierungen von <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle X}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>X</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle X}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/68baa052181f707c662844a465bfeeb135e82bab.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.338ex; width:1.98ex; height:2.176ex;" alt="{\displaystyle X}" loading="lazy"></span> und <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle Y}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>Y</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle Y}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/961d67d6b454b4df2301ac571808a3538b3a6d3f.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.171ex; width:1.773ex; height:2.009ex;" alt="{\displaystyle Y}" loading="lazy"></span>. Die Studie könnte wiederholt werden, aber das ist zeitaufwendig und ggf. teuer. Hier hilft die parametrische Bootstrap-Methode. Man schätzt zunächst <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle p}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>p</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle p}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/81eac1e205430d1f40810df36a0edffdc367af36.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.671ex; margin-left: -0.089ex; width:1.259ex; height:2.009ex;" alt="{\displaystyle p}" loading="lazy"></span> und <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle q}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>q</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle q}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/06809d64fa7c817ffc7e323f85997f783dbdf71d.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.671ex; width:1.07ex; height:2.009ex;" alt="{\displaystyle q}" loading="lazy"></span> mit den Daten, die wir beobachtet haben. So erhält man <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle {\hat {p}}=104/11037}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mrow class="MJX-TeXAtom-ORD">
<mrow class="MJX-TeXAtom-ORD">
<mover>
<mi>p</mi>
<mo stretchy="false">^<!-- ^ --></mo>
</mover>
</mrow>
</mrow>
<mo>=</mo>
<mn>104</mn>
<mrow class="MJX-TeXAtom-ORD">
<mo>/</mo>
</mrow>
<mn>11037</mn>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle {\hat {p}}=104/11037}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/cbd77fdf22e235713e97de3c32412ef63dbc7f3a.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.838ex; margin-left: -0.089ex; width:15.009ex; height:2.843ex;" alt="{\displaystyle {\hat {p}}=104/11037}" loading="lazy"></span> und <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle {\hat {q}}=189/11034}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mrow class="MJX-TeXAtom-ORD">
<mrow class="MJX-TeXAtom-ORD">
<mover>
<mi>q</mi>
<mo stretchy="false">^<!-- ^ --></mo>
</mover>
</mrow>
</mrow>
<mo>=</mo>
<mn>189</mn>
<mrow class="MJX-TeXAtom-ORD">
<mo>/</mo>
</mrow>
<mn>11034</mn>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle {\hat {q}}=189/11034}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/f97c3e012b25ad93b0f16c8b2da15310f8e75b83.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.838ex; width:14.938ex; height:2.843ex;" alt="{\displaystyle {\hat {q}}=189/11034}" loading="lazy"></span>. Anstelle von <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle (X,Y)}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mo stretchy="false">(</mo>
<mi>X</mi>
<mo>,</mo>
<mi>Y</mi>
<mo stretchy="false">)</mo>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle (X,Y)}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/41f29b9537685f499713112d6802e811cbf51bba.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.838ex; width:6.597ex; height:2.843ex;" alt="{\displaystyle (X,Y)}" loading="lazy"></span> simulieren wir nun mit der Bootstrap-Variante <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle (X^{*},Y^{*})}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mo stretchy="false">(</mo>
<msup>
<mi>X</mi>
<mrow class="MJX-TeXAtom-ORD">
<mo>∗<!-- ∗ --></mo>
</mrow>
</msup>
<mo>,</mo>
<msup>
<mi>Y</mi>
<mrow class="MJX-TeXAtom-ORD">
<mo>∗<!-- ∗ --></mo>
</mrow>
</msup>
<mo stretchy="false">)</mo>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle (X^{*},Y^{*})}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/9ad76f78d4d76a306effb589ce2a00de47d1c2c5.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.838ex; width:8.849ex; height:2.843ex;" alt="{\displaystyle (X^{*},Y^{*})}" loading="lazy"></span>, wobei <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle X^{*}\sim \operatorname {Bin} (11037,{\hat {p}})}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msup>
<mi>X</mi>
<mrow class="MJX-TeXAtom-ORD">
<mo>∗<!-- ∗ --></mo>
</mrow>
</msup>
<mo>∼<!-- ∼ --></mo>
<mi>Bin</mi>
<mo>⁡<!-- ⁡ --></mo>
<mo stretchy="false">(</mo>
<mn>11037</mn>
<mo>,</mo>
<mrow class="MJX-TeXAtom-ORD">
<mrow class="MJX-TeXAtom-ORD">
<mover>
<mi>p</mi>
<mo stretchy="false">^<!-- ^ --></mo>
</mover>
</mrow>
</mrow>
<mo stretchy="false">)</mo>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle X^{*}\sim \operatorname {Bin} (11037,{\hat {p}})}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/9a23b6d6ffae23f7034f2792f79e8f0da7015fcd.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.838ex; width:19.749ex; height:2.843ex;" alt="{\displaystyle X^{*}\sim \operatorname {Bin} (11037,{\hat {p}})}" loading="lazy"></span> und <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle Y^{*}\sim \operatorname {Bin} (11034,{\hat {q}})}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msup>
<mi>Y</mi>
<mrow class="MJX-TeXAtom-ORD">
<mo>∗<!-- ∗ --></mo>
</mrow>
</msup>
<mo>∼<!-- ∼ --></mo>
<mi>Bin</mi>
<mo>⁡<!-- ⁡ --></mo>
<mo stretchy="false">(</mo>
<mn>11034</mn>
<mo>,</mo>
<mrow class="MJX-TeXAtom-ORD">
<mrow class="MJX-TeXAtom-ORD">
<mover>
<mi>q</mi>
<mo stretchy="false">^<!-- ^ --></mo>
</mover>
</mrow>
</mrow>
<mo stretchy="false">)</mo>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle Y^{*}\sim \operatorname {Bin} (11034,{\hat {q}})}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/c97a03b44d68d0a8347273c8bb943a55e4a20489.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.838ex; width:19.67ex; height:2.843ex;" alt="{\displaystyle Y^{*}\sim \operatorname {Bin} (11034,{\hat {q}})}" loading="lazy"></span>. Über <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle t_{i}^{*}={\frac {x_{i}^{*}/11037}{y_{i}^{*}/11034}}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msubsup>
<mi>t</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>i</mi>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mo>∗<!-- ∗ --></mo>
</mrow>
</msubsup>
<mo>=</mo>
<mrow class="MJX-TeXAtom-ORD">
<mfrac>
<mrow>
<msubsup>
<mi>x</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>i</mi>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mo>∗<!-- ∗ --></mo>
</mrow>
</msubsup>
<mrow class="MJX-TeXAtom-ORD">
<mo>/</mo>
</mrow>
<mn>11037</mn>
</mrow>
<mrow>
<msubsup>
<mi>y</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>i</mi>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mo>∗<!-- ∗ --></mo>
</mrow>
</msubsup>
<mrow class="MJX-TeXAtom-ORD">
<mo>/</mo>
</mrow>
<mn>11034</mn>
</mrow>
</mfrac>
</mrow>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle t_{i}^{*}={\frac {x_{i}^{*}/11037}{y_{i}^{*}/11034}}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/b53ac2b0ba651bef1b136995a864ddcc941530ae.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -2.838ex; width:15.187ex; height:6.843ex;" alt="{\displaystyle t_{i}^{*}={\frac {x_{i}^{*}/11037}{y_{i}^{*}/11034}}}" loading="lazy"></span> mit <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle i=1,2,\dots ,B}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
<mo>,</mo>
<mn>2</mn>
<mo>,</mo>
<mo>…<!-- … --></mo>
<mo>,</mo>
<mi>B</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle i=1,2,\dots ,B}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/bdc157318f3b1b9f71d1ec967e2d1374343706d3.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.671ex; width:14.202ex; height:2.509ex;" alt="{\displaystyle i=1,2,\dots ,B}" loading="lazy"></span> erhält man Bootstrap-Realisierungen <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle t_{1}^{*},\dots ,t_{B}^{*}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msubsup>
<mi>t</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>1</mn>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mo>∗<!-- ∗ --></mo>
</mrow>
</msubsup>
<mo>,</mo>
<mo>…<!-- … --></mo>
<mo>,</mo>
<msubsup>
<mi>t</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>B</mi>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mo>∗<!-- ∗ --></mo>
</mrow>
</msubsup>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle t_{1}^{*},\dots ,t_{B}^{*}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/6c28d06c1ae75aca0b22db008003adbb9bc30a22.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -1.005ex; width:9.391ex; height:2.843ex;" alt="{\displaystyle t_{1}^{*},\dots ,t_{B}^{*}}" loading="lazy"></span> von <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle T}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>T</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle T}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/ec7200acd984a1d3a3d7dc455e262fbe54f7f6e0.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.338ex; width:1.636ex; height:2.176ex;" alt="{\displaystyle T}" loading="lazy"></span>. Der <a href="Empirischer_Mittelwert" class="mw-redirect" title="Empirischer Mittelwert">empirische Mittelwert</a> und die <a href="Empirische_Varianz" title="Empirische Varianz">empirische Varianz</a> dieser Datenpunkte sind nun Schätzwerte für den theoretischen <a href="Erwartungswert" title="Erwartungswert">Erwartungswert</a> bzw. die theoretische <a href="Varianz" title="Varianz">Varianz</a>. Weiterhin lässt sich das gesuchte Konfidenzintervall für <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle p/q}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>p</mi>
<mrow class="MJX-TeXAtom-ORD">
<mo>/</mo>
</mrow>
<mi>q</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle p/q}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/8fa5bd4cf049744deac0ac4a04c07998bd6befa9.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.838ex; margin-left: -0.089ex; width:3.491ex; height:2.843ex;" alt="{\displaystyle p/q}" loading="lazy"></span> über die <a href="Empirisches_Quantil" title="Empirisches Quantil">empirischen Quantile</a> konstruieren.
</p>
<div class="mw-heading mw-heading2"><h2 id="Bootstrap-Test">Bootstrap-Test</h2></div>
<p>Gegeben zwei Stichproben aus den Verteilungen <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle F}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>F</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle F}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/545fd099af8541605f7ee55f08225526be88ce57.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.338ex; width:1.741ex; height:2.176ex;" alt="{\displaystyle F}" loading="lazy"></span> und <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle G}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>G</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle G}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/f5f3c8921a3b352de45446a6789b104458c9f90b.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.338ex; width:1.827ex; height:2.176ex;" alt="{\displaystyle G}" loading="lazy"></span>, verläuft ein Bootstrap-Test für die Nullhypothese <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle H_{0}:F=G}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msub>
<mi>H</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>0</mn>
</mrow>
</msub>
<mo>:</mo>
<mi>F</mi>
<mo>=</mo>
<mi>G</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle H_{0}:F=G}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/9b587413f1bf05485516f44cd01072ad44cca27c.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.671ex; width:11.589ex; height:2.509ex;" alt="{\displaystyle H_{0}:F=G}" loading="lazy"></span> wie ein <a href="Permutationstest" title="Permutationstest">Permutationstest</a>, allerdings mit <a href="Ziehen_mit_Zur%C3%BCcklegen" class="mw-redirect" title="Ziehen mit Zurücklegen">Ziehen mit Zurücklegen</a> aus dem fusionierten Datensatz anstelle von <a href="Permutation" title="Permutation">Permutationen</a>.
</p><p>Bootstrap-Tests können auch die Nullhypothese <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle H_{0}:F\neq G}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msub>
<mi>H</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>0</mn>
</mrow>
</msub>
<mo>:</mo>
<mi>F</mi>
<mo>≠<!-- ≠ --></mo>
<mi>G</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle H_{0}:F\neq G}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/fceb6ecc6593234232b2bff77805f2931a4faa49.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.838ex; width:11.589ex; height:2.676ex;" alt="{\displaystyle H_{0}:F\neq G}" loading="lazy"></span> testen und somit für <a href="%C3%84quivalenztest" title="Äquivalenztest">Äquivalenztests</a> benutzt werden.
</p>
<div class="mw-heading mw-heading2"><h2 id="Theoretischer_Hintergrund">Theoretischer Hintergrund</h2></div>
<p>Theoretisch ist das Bootstrapping-Verfahren durch den <a href="Satz_von_Gliwenko-Cantelli" title="Satz von Gliwenko-Cantelli">Satz von Gliwenko-Cantelli</a> gestützt.<sup id="cite_ref-15" class="reference"><a href="#cite_note-15"><span class="cite-bracket">[</span>15<span class="cite-bracket">]</span></a></sup>
</p>
<div class="mw-heading mw-heading2"><h2 id="Probleme">Probleme</h2></div>
<p>In hohen Dimensionen ist Residual-Bootstrap (eine Methode zum Bootstrappen von Regressionsmodellen)<sup id="cite_ref-16" class="reference"><a href="#cite_note-16"><span class="cite-bracket">[</span>16<span class="cite-bracket">]</span></a></sup> sehr <a href="%C3%9Cberdeckungswahrscheinlichkeit" title="Überdeckungswahrscheinlichkeit">anti-konservativ</a> bzw. Pair-Bootstrap sehr <a href="%C3%9Cberdeckungswahrscheinlichkeit" title="Überdeckungswahrscheinlichkeit">konservativ</a><sup id="cite_ref-17" class="reference"><a href="#cite_note-17"><span class="cite-bracket">[</span>17<span class="cite-bracket">]</span></a></sup>.
</p><p>Bei der <a href="Stichprobenwiederholung" class="mw-redirect" title="Stichprobenwiederholung">Stichprobenwiederholung</a> mit Zurücklegen gilt für eine Stichprobe der Größe <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle n}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>n</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle n}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/a601995d55609f2d9f5e233e36fbe9ea26011b3b.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.338ex; width:1.395ex; height:1.676ex;" alt="{\displaystyle n}" loading="lazy"></span>, dass die Wahrscheinlichkeit für ein Sample, nicht ausgewählt zu werden, <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle p=1-1/n}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>p</mi>
<mo>=</mo>
<mn>1</mn>
<mo>−<!-- − --></mo>
<mn>1</mn>
<mrow class="MJX-TeXAtom-ORD">
<mo>/</mo>
</mrow>
<mi>n</mi>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle p=1-1/n}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/24cfa7fedb0f079f9e046d613cd127e04a33c136.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.838ex; margin-left: -0.089ex; width:12.08ex; height:2.843ex;" alt="{\displaystyle p=1-1/n}" loading="lazy"></span> ist. Somit ist bei einer Stichprobenwiederholung mit Zurücklegen die Wahrscheinlichkeit, dass der Wert n-mal nicht ausgewählt wird (für große Stichprobenumfänge im Limes) <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle \lim _{n\to \infty }(1-1/n)^{n}=e^{-1}\approx 0{,}368=1-0{,}632}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<munder>
<mo movablelimits="true" form="prefix">lim</mo>
<mrow class="MJX-TeXAtom-ORD">
<mi>n</mi>
<mo stretchy="false">→<!-- → --></mo>
<mi mathvariant="normal">∞<!-- ∞ --></mi>
</mrow>
</munder>
<mo stretchy="false">(</mo>
<mn>1</mn>
<mo>−<!-- − --></mo>
<mn>1</mn>
<mrow class="MJX-TeXAtom-ORD">
<mo>/</mo>
</mrow>
<mi>n</mi>
<msup>
<mo stretchy="false">)</mo>
<mrow class="MJX-TeXAtom-ORD">
<mi>n</mi>
</mrow>
</msup>
<mo>=</mo>
<msup>
<mi>e</mi>
<mrow class="MJX-TeXAtom-ORD">
<mo>−<!-- − --></mo>
<mn>1</mn>
</mrow>
</msup>
<mo>≈<!-- ≈ --></mo>
<mn>0,368</mn>
<mo>=</mo>
<mn>1</mn>
<mo>−<!-- − --></mo>
<mn>0,632</mn>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle \lim _{n\to \infty }(1-1/n)^{n}=e^{-1}\approx 0{,}368=1-0{,}632}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/ee786bf74a77a85b971eee84c3d0654e2dd5fe41.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -1.838ex; width:42.331ex; height:4.176ex;" alt="{\displaystyle \lim _{n\to \infty }(1-1/n)^{n}=e^{-1}\approx 0{,}368=1-0{,}632}" loading="lazy"></span>. Daher enthält eine Stichprobenwiederholung im Schnitt nur 63,2&nbsp;% der zugrundeliegenden Werte (wobei diese dann auch mehrfach vorliegen dürfen). Dies führt zu Korrekturen wie dem 632 Bootstrap zum Abschätzen des Generalisierungsfehlers eines gefitteten Modells<sup id="cite_ref-18" class="reference"><a href="#cite_note-18"><span class="cite-bracket">[</span>18<span class="cite-bracket">]</span></a></sup>.
</p><p>Die Größe der Bootstrap-Stichprobe kann zum Beispiel beim Bootstrapping der Verteilung von Extremwerten Einfluss auf das Ergebnis haben, dort muss die Bootstrap-Stichproben-Größe kleiner sein als die originale Stichprobengröße, um konsistente Ergebnisse zu erhalten.<sup id="cite_ref-19" class="reference"><a href="#cite_note-19"><span class="cite-bracket">[</span>19<span class="cite-bracket">]</span></a></sup>
</p>
<div class="mw-heading mw-heading2"><h2 id="Endliche_Grundgesamtheit">Endliche Grundgesamtheit</h2></div>
<p>Um Bootstrapping auch mit <a href="Grundgesamtheit" title="Grundgesamtheit">endlichen Grundgesamtheiten</a>, bei denen Stichproben durch <a href="Ziehen_ohne_Zur%C3%BCcklegen" class="mw-redirect" title="Ziehen ohne Zurücklegen">Ziehen ohne Zurücklegen</a> gezogen wurden, anwenden zu können, sind Anpassungen erforderlich. Die i.i.d Annahme des Bootstrapping-Verfahrens würden hier <a href="Ziehen_mit_Zur%C3%BCcklegen" class="mw-redirect" title="Ziehen mit Zurücklegen">Ziehen mit Zurücklegen</a> erfordern (nicht Ziehen ohne Zurücklegen).
Ein Beispiel für eine Anpassung des Bootstrap auf endliche Grundgesamtheit und Ziehen ohne Zurücklegen ist das "population bootstrap"<sup id="cite_ref-20" class="reference"><a href="#cite_note-20"><span class="cite-bracket">[</span>20<span class="cite-bracket">]</span></a></sup>.
</p>
<div class="mw-heading mw-heading2"><h2 id="Literatur">Literatur</h2></div>
<ul><li>Felix Bittmann: <cite style="font-style:italic">Bootstrapping - An Integrated Approach with Python and Stata</cite>. De Gruyter, 2021.<span class="Z3988" title="ctx_ver=Z39.88-2004&amp;rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&amp;rfr_id=info:sid/de.wikipedia.org:Bootstrapping-Verfahren&amp;rft.au=Felix+Bittmann&amp;rft.btitle=Bootstrapping+-+An+Integrated+Approach+with+Python+and+Stata&amp;rft.date=2021&amp;rft.genre=book&amp;rft.pub=De+Gruyter" style="display:none">&nbsp;</span></li>
<li><a href="Bradley_Efron" title="Bradley Efron">Bradley Efron</a>: <cite style="font-style:italic">Bootstrap Methods: Another Look at the Jackknife</cite>. In: <cite style="font-style:italic"><a href="The_Annals_of_Statistics" title="The Annals of Statistics">The Annals of Statistics</a></cite>. <span style="white-space:nowrap">Band<span style="display:inline-block;width:.2em">&nbsp;</span>7</span>, <span style="white-space:nowrap">Nr.<span style="display:inline-block;width:.2em">&nbsp;</span>1</span>, 1979, <span style="white-space:nowrap">S.<span style="display:inline-block;width:.2em">&nbsp;</span>1–26</span>, <a href="Digital_Object_Identifier" title="Digital Object Identifier">doi</a>:<span class="uri-handle" style="white-space:nowrap"><a rel="nofollow" class="external text" href="https://doi.org/10.1214/aos%2F1176344552">10.1214/aos/1176344552</a></span>.<span class="Z3988" title="ctx_ver=Z39.88-2004&amp;rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&amp;rfr_id=info:sid/de.wikipedia.org:Bootstrapping-Verfahren&amp;rft.atitle=Bootstrap+Methods%3A+Another+Look+at+the+Jackknife&amp;rft.au=Bradley+Efron&amp;rft.date=1979&amp;rft.doi=10.1214%2Faos%2F1176344552&amp;rft.genre=journal&amp;rft.issue=1&amp;rft.jtitle=The+Annals+of+Statistics&amp;rft.pages=1-26&amp;rft.volume=7" style="display:none">&nbsp;</span></li>
<li>Bradley Efron, Robert J. Tibshirani: <cite style="font-style:italic">An Introduction to the Bootstrap</cite>. Chapman &amp; Hall, New York 1993.<span class="Z3988" title="ctx_ver=Z39.88-2004&amp;rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&amp;rfr_id=info:sid/de.wikipedia.org:Bootstrapping-Verfahren&amp;rft.au=Bradley+Efron%2C+Robert+J.+Tibshirani&amp;rft.btitle=An+Introduction+to+the+Bootstrap&amp;rft.date=1993&amp;rft.genre=book&amp;rft.place=New+York&amp;rft.pub=Chapman+%26+Hall" style="display:none">&nbsp;</span></li>
<li>Jun Shao, Dongsheng Tu: <cite style="font-style:italic">The Jackknife and Bootstrap</cite>. Springer, 1995.<span class="Z3988" title="ctx_ver=Z39.88-2004&amp;rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&amp;rfr_id=info:sid/de.wikipedia.org:Bootstrapping-Verfahren&amp;rft.au=Jun+Shao%2C+Dongsheng+Tu&amp;rft.btitle=The+Jackknife+and+Bootstrap&amp;rft.date=1995&amp;rft.genre=book&amp;rft.pub=Springer" style="display:none">&nbsp;</span></li>
<li>A. C. Davison, D. V. Hinkley: <cite style="font-style:italic">Bootstrap Methods and their Application</cite> (=&nbsp;<cite style="font-style:italic">Cambridge Series in Statistical and Probability Mathematics</cite>. <span style="white-space:nowrap">Band<span style="display:inline-block;width:.2em">&nbsp;</span>1</span>). Cambridge University Press, 1997, <a href="Digital_Object_Identifier" title="Digital Object Identifier">doi</a>:<span class="uri-handle" style="white-space:nowrap"><a rel="nofollow" class="external text" href="https://doi.org/10.1017/CBO9780511802843">10.1017/CBO9780511802843</a></span>.<span class="Z3988" title="ctx_ver=Z39.88-2004&amp;rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&amp;rfr_id=info:sid/de.wikipedia.org:Bootstrapping-Verfahren&amp;rft.au=A.+C.+Davison%2C+D.+V.+Hinkley&amp;rft.btitle=Bootstrap+Methods+and+their+Application&amp;rft.date=1997&amp;rft.doi=10.1017%2FCBO9780511802843&amp;rft.genre=book&amp;rft.pub=Cambridge+University+Press&amp;rft.series=Cambridge+Series+in+Statistical+and+Probability+Mathematics" style="display:none">&nbsp;</span></li>
<li>Gail Gong (1986) Cross-Validation, the Jackknife, and the Bootstrap: Excess Error Estimation in Forward Logistic Regression, Journal of the American Statistical Association, 81:393, 108-113, <a href="https://doi.org/10.1080/01621459.1986.10478245" class="extiw external" title="doi:10.1080/01621459.1986.10478245">DOI:10.1080/01621459.1986.10478245</a></li></ul>
<div class="mw-heading mw-heading2"><h2 id="Weblinks">Weblinks</h2></div>
<ul><li><a rel="nofollow" class="external text" href="https://projecteuclid.org/euclid.ss/1063994964">Ausgabe des Journals <i>Statistical Science</i> anlässlich des 25-jährigen Jubiläums der Bootstrap-Methode</a> (Statist. Sci. 18(2), Mai 2003)</li></ul>
<div class="mw-heading mw-heading2"><h2 id="Einzelnachweise">Einzelnachweise</h2></div>
<ol class="references">
<li id="cite_note-1"><span class="mw-cite-backlink"><a href="#cite_ref-1">↑</a></span> <span class="reference-text">Bradley Efron: <cite style="font-style:italic">Bootstrap Methods: Another Look at the Jackknife</cite>. In: <cite style="font-style:italic">The Annals of Statistics</cite>. <span style="white-space:nowrap">Band<span style="display:inline-block;width:.2em">&nbsp;</span>7</span>, <span style="white-space:nowrap">Nr.<span style="display:inline-block;width:.2em">&nbsp;</span>1</span>, 1.&nbsp;Januar 1979, <a href="Internationale_Standardnummer_f%C3%BCr_fortlaufende_Sammelwerke" title="Internationale Standardnummer für fortlaufende Sammelwerke">ISSN</a>&nbsp;<span style="white-space:nowrap"><a rel="nofollow" class="external text" href="https://zdb-katalog.de/list.xhtml?t=iss%3D%220090-5364%22&amp;key=cql">0090-5364</a></span>, <a href="Digital_Object_Identifier" title="Digital Object Identifier">doi</a>:<span class="uri-handle" style="white-space:nowrap"><a rel="nofollow" class="external text" href="https://doi.org/10.1214/aos%2F1176344552">10.1214/aos/1176344552</a></span> (<a rel="nofollow" class="external text" href="https://projecteuclid.org/journals/annals-of-statistics/volume-7/issue-1/Bootstrap-Methods-Another-Look-at-the-Jackknife/10.1214/aos/1176344552.full">projecteuclid.org</a>).<span class="Z3988" title="ctx_ver=Z39.88-2004&amp;rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&amp;rfr_id=info:sid/de.wikipedia.org:Bootstrapping-Verfahren&amp;rft.atitle=Bootstrap+Methods%3A+Another+Look+at+the+Jackknife&amp;rft.au=Bradley+Efron&amp;rft.date=1979-01-01&amp;rft.doi=10.1214%2Faos%2F1176344552&amp;rft.genre=journal&amp;rft.issn=0090-5364&amp;rft.issue=1&amp;rft.jtitle=The+Annals+of+Statistics&amp;rft.volume=7" style="display:none">&nbsp;</span></span>
</li>
<li id="cite_note-Efron_2003-2"><span class="mw-cite-backlink">↑ <sup><a href="#cite_ref-Efron_2003_2-0">a</a></sup> <sup><a href="#cite_ref-Efron_2003_2-1">b</a></sup></span> <span class="reference-text">Bradley Efron: <cite style="font-style:italic">Second Thoughts on the Bootstrap</cite>. In: <cite style="font-style:italic">Statistical Science</cite>. <span style="white-space:nowrap">Band<span style="display:inline-block;width:.2em">&nbsp;</span>18</span>, <span style="white-space:nowrap">Nr.<span style="display:inline-block;width:.2em">&nbsp;</span>2</span>, 1.&nbsp;Mai 2003, <a href="Internationale_Standardnummer_f%C3%BCr_fortlaufende_Sammelwerke" title="Internationale Standardnummer für fortlaufende Sammelwerke">ISSN</a>&nbsp;<span style="white-space:nowrap"><a rel="nofollow" class="external text" href="https://zdb-katalog.de/list.xhtml?t=iss%3D%220883-4237%22&amp;key=cql">0883-4237</a></span>, <a href="Digital_Object_Identifier" title="Digital Object Identifier">doi</a>:<span class="uri-handle" style="white-space:nowrap"><a rel="nofollow" class="external text" href="https://doi.org/10.1214/ss%2F1063994968">10.1214/ss/1063994968</a></span>.<span class="Z3988" title="ctx_ver=Z39.88-2004&amp;rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&amp;rfr_id=info:sid/de.wikipedia.org:Bootstrapping-Verfahren&amp;rft.atitle=Second+Thoughts+on+the+Bootstrap&amp;rft.au=Bradley+Efron&amp;rft.date=2003-05-01&amp;rft.doi=10.1214%2Fss%2F1063994968&amp;rft.genre=journal&amp;rft.issn=0883-4237&amp;rft.issue=2&amp;rft.jtitle=Statistical+Science&amp;rft.volume=18" style="display:none">&nbsp;</span></span>
</li>
<li id="cite_note-3"><span class="mw-cite-backlink"><a href="#cite_ref-3">↑</a></span> <span class="reference-text">William Howard Beasley, Joseph Lee Rodgers: <cite style="font-style:italic">Bootstrapping and Monte Carlo methods.</cite> In: <cite style="font-style:italic">APA handbook of research methods in psychology, Vol 2: Research designs: Quantitative, qualitative, neuropsychological, and biological.</cite> American Psychological Association, Washington 2012, <span style="white-space:nowrap">S.<span style="display:inline-block;width:.2em">&nbsp;</span>407–425</span>, <a href="Digital_Object_Identifier" title="Digital Object Identifier">doi</a>:<span class="uri-handle" style="white-space:nowrap"><a rel="nofollow" class="external text" href="https://doi.org/10.1037/13620-022">10.1037/13620-022</a></span>.<span class="Z3988" title="ctx_ver=Z39.88-2004&amp;rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&amp;rfr_id=info:sid/de.wikipedia.org:Bootstrapping-Verfahren&amp;rft.atitle=Bootstrapping+and+Monte+Carlo+methods.&amp;rft.au=William+Howard+Beasley%2C+Joseph+Lee+Rodgers&amp;rft.btitle=APA+handbook+of+research+methods+in+psychology%2C+Vol+2%3A+Research+designs%3A+Quantitative%2C+qualitative%2C+neuropsychological%2C+and+biological.&amp;rft.date=2012&amp;rft.doi=10.1037%2F13620-022&amp;rft.genre=book&amp;rft.pages=407-425&amp;rft.place=Washington&amp;rft.pub=American+Psychological+Association" style="display:none">&nbsp;</span></span>
</li>
<li id="cite_note-4"><span class="mw-cite-backlink"><a href="#cite_ref-4">↑</a></span> <span class="reference-text">K. B. Athreya: <cite style="font-style:italic">Bootstrap of the Mean in the Infinite Variance Case</cite>. In: <cite style="font-style:italic">The Annals of Statistics</cite>. <span style="white-space:nowrap">Band<span style="display:inline-block;width:.2em">&nbsp;</span>15</span>, <span style="white-space:nowrap">Nr.<span style="display:inline-block;width:.2em">&nbsp;</span>2</span>, 1.&nbsp;Juni 1987, <a href="Internationale_Standardnummer_f%C3%BCr_fortlaufende_Sammelwerke" title="Internationale Standardnummer für fortlaufende Sammelwerke">ISSN</a>&nbsp;<span style="white-space:nowrap"><a rel="nofollow" class="external text" href="https://zdb-katalog.de/list.xhtml?t=iss%3D%220090-5364%22&amp;key=cql">0090-5364</a></span>, <a href="Digital_Object_Identifier" title="Digital Object Identifier">doi</a>:<span class="uri-handle" style="white-space:nowrap"><a rel="nofollow" class="external text" href="https://doi.org/10.1214/aos%2F1176350371">10.1214/aos/1176350371</a></span>.<span class="Z3988" title="ctx_ver=Z39.88-2004&amp;rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&amp;rfr_id=info:sid/de.wikipedia.org:Bootstrapping-Verfahren&amp;rft.atitle=Bootstrap+of+the+Mean+in+the+Infinite+Variance+Case&amp;rft.au=K.+B.+Athreya&amp;rft.date=1987-06-01&amp;rft.doi=10.1214%2Faos%2F1176350371&amp;rft.genre=journal&amp;rft.issn=0090-5364&amp;rft.issue=2&amp;rft.jtitle=The+Annals+of+Statistics&amp;rft.volume=15" style="display:none">&nbsp;</span></span>
</li>
<li id="cite_note-5"><span class="mw-cite-backlink"><a href="#cite_ref-5">↑</a></span> <span class="reference-text">Maria Dolores Ugarte, Ana F. Militino, Alan T. Arnholt: <cite style="font-style:italic">Probability and Statistics with R</cite>. Hrsg.: CRC Press. 2015, ISBN 978-1-4665-0440-0, <span style="white-space:nowrap">S.<span style="display:inline-block;width:.2em">&nbsp;</span>656</span>.<span class="Z3988" title="ctx_ver=Z39.88-2004&amp;rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&amp;rfr_id=info:sid/de.wikipedia.org:Bootstrapping-Verfahren&amp;rft.au=Maria+Dolores+Ugarte%2C+Ana+F.+Militino%2C+Alan+T.+Arnholt&amp;rft.btitle=Probability+and+Statistics+with+R&amp;rft.date=2015&amp;rft.genre=book&amp;rft.isbn=9781466504400&amp;rft.pages=656" style="display:none">&nbsp;</span></span>
</li>
<li id="cite_note-6"><span class="mw-cite-backlink"><a href="#cite_ref-6">↑</a></span> <span class="reference-text">Boos, D. D., Stefanski, L. A. (2013). Essential Statistical Inference: Theory and Methods. Niederlande: Springer New York., Seite 413, <a rel="nofollow" class="external free" href="https://www.google.de/books/edition/Essential_Statistical_Inference/8VNDAAAAQBAJ?hl=de&amp;gbpv=1&amp;dq=parallel%20worlds%2C%20bootstrap%20statistic&amp;pg=PA413">https://www.google.de/books/edition/Essential_Statistical_Inference/8VNDAAAAQBAJ?hl=de&amp;gbpv=1&amp;dq=parallel%20worlds%2C%20bootstrap%20statistic&amp;pg=PA413</a></span>
</li>
<li id="cite_note-7"><span class="mw-cite-backlink"><a href="#cite_ref-7">↑</a></span> <span class="reference-text">Frank A. Sortino, Stephen E. Satchel: <cite style="font-style:italic">Managing downside risk in financial markets, Theory, Practice and Implementation, Artikel: Chapter 4, The mathematician' view: Modelling uncertainty with the three parameter lognormal</cite>. Hrsg.: Frank A. Sortino and Stephen E. Satchel. 2005, ISBN 0-7506-4863-5, <span style="white-space:nowrap">S.<span style="display:inline-block;width:.2em">&nbsp;</span>51–58</span>.<span class="Z3988" title="ctx_ver=Z39.88-2004&amp;rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&amp;rfr_id=info:sid/de.wikipedia.org:Bootstrapping-Verfahren&amp;rft.au=Frank+A.+Sortino%2C+Stephen+E.+Satchel&amp;rft.btitle=Managing+downside+risk+in+financial+markets%2C+Theory%2C+Practice+and+Implementation%2C+Artikel%3A+Chapter+4%2C+The+mathematician%27+view%3A+Modelling+uncertainty+with+the+three+parameter+lognormal&amp;rft.date=2005&amp;rft.genre=book&amp;rft.isbn=0750648635&amp;rft.pages=51-58" style="display:none">&nbsp;</span></span>
</li>
<li id="cite_note-8"><span class="mw-cite-backlink"><a href="#cite_ref-8">↑</a></span> <span class="reference-text">Efron, Bradley.: <cite style="font-style:italic">An introduction to the bootstrap</cite>. Chapman &amp; Hall/CRC, 1998, ISBN 0-412-04231-2.<span class="Z3988" title="ctx_ver=Z39.88-2004&amp;rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&amp;rfr_id=info:sid/de.wikipedia.org:Bootstrapping-Verfahren&amp;rft.au=Efron%2C+Bradley.&amp;rft.btitle=An+introduction+to+the+bootstrap&amp;rft.date=1998&amp;rft.genre=book&amp;rft.isbn=0412042312&amp;rft.pub=Chapman+%26+Hall%2FCRC" style="display:none">&nbsp;</span></span>
</li>
<li id="cite_note-9"><span class="mw-cite-backlink"><a href="#cite_ref-9">↑</a></span> <span class="reference-text">Ohne beachten der Reihenfolge ist die Zahl der möglichen Stichprobenwiederholungen <span class="mwe-math-element mwe-math-element-inline"><span class="mwe-math-mathml-inline mwe-math-mathml-a11y" style="display: none;"><math xmlns="http://www.w3.org/1998/Math/MathML" alttext="{\displaystyle {2n-1} \choose {n-1}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mrow>
<mrow class="MJX-TeXAtom-OPEN">
<mo maxsize="2.047em" minsize="2.047em">(</mo>
</mrow>
<mfrac linethickness="0">
<mstyle displaystyle="true" scriptlevel="0">
<mrow class="MJX-TeXAtom-ORD">
<mn>2</mn>
<mi>n</mi>
<mo>−<!-- − --></mo>
<mn>1</mn>
</mrow>
</mstyle>
<mrow class="MJX-TeXAtom-ORD">
<mi>n</mi>
<mo>−<!-- − --></mo>
<mn>1</mn>
</mrow>
</mfrac>
<mrow class="MJX-TeXAtom-CLOSE">
<mo maxsize="2.047em" minsize="2.047em">)</mo>
</mrow>
</mrow>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle {2n-1} \choose {n-1}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/c815487fa89a4ff14cc908abb170741a8f780370.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -2.505ex; width:9.981ex; height:6.176ex;" alt="{\displaystyle {2n-1} \choose {n-1}}" loading="lazy"></span></span>
</li>
<li id="cite_note-10"><span class="mw-cite-backlink"><a href="#cite_ref-10">↑</a></span> <span class="reference-text">Hans R. Kunsch: <cite style="font-style:italic">The Jackknife and the Bootstrap for General Stationary Observations</cite>. In: <cite style="font-style:italic">The Annals of Statistics</cite>. <span style="white-space:nowrap">Band<span style="display:inline-block;width:.2em">&nbsp;</span>17</span>, <span style="white-space:nowrap">Nr.<span style="display:inline-block;width:.2em">&nbsp;</span>3</span>, 1.&nbsp;September 1989, <a href="Internationale_Standardnummer_f%C3%BCr_fortlaufende_Sammelwerke" title="Internationale Standardnummer für fortlaufende Sammelwerke">ISSN</a>&nbsp;<span style="white-space:nowrap"><a rel="nofollow" class="external text" href="https://zdb-katalog.de/list.xhtml?t=iss%3D%220090-5364%22&amp;key=cql">0090-5364</a></span>, <a href="Digital_Object_Identifier" title="Digital Object Identifier">doi</a>:<span class="uri-handle" style="white-space:nowrap"><a rel="nofollow" class="external text" href="https://doi.org/10.1214/aos%2F1176347265">10.1214/aos/1176347265</a></span>.<span class="Z3988" title="ctx_ver=Z39.88-2004&amp;rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&amp;rfr_id=info:sid/de.wikipedia.org:Bootstrapping-Verfahren&amp;rft.atitle=The+Jackknife+and+the+Bootstrap+for+General+Stationary+Observations&amp;rft.au=Hans+R.+Kunsch&amp;rft.date=1989-09-01&amp;rft.doi=10.1214%2Faos%2F1176347265&amp;rft.genre=journal&amp;rft.issn=0090-5364&amp;rft.issue=3&amp;rft.jtitle=The+Annals+of+Statistics&amp;rft.volume=17" style="display:none">&nbsp;</span></span>
</li>
<li id="cite_note-11"><span class="mw-cite-backlink"><a href="#cite_ref-11">↑</a></span> <span class="reference-text">S. Mignani, R. Rosa: <cite style="font-style:italic">The moving block bootstrap to assess the accuracy of statistical estimates in Ising model simulations</cite>. In: <cite style="font-style:italic">Computer Physics Communications</cite>. <span style="white-space:nowrap">Band<span style="display:inline-block;width:.2em">&nbsp;</span>92</span>, <span style="white-space:nowrap">Nr.<span style="display:inline-block;width:.2em">&nbsp;</span>2–3</span>, Dezember 1995, <a href="Internationale_Standardnummer_f%C3%BCr_fortlaufende_Sammelwerke" title="Internationale Standardnummer für fortlaufende Sammelwerke">ISSN</a>&nbsp;<span style="white-space:nowrap"><a rel="nofollow" class="external text" href="https://zdb-katalog.de/list.xhtml?t=iss%3D%220010-4655%22&amp;key=cql">0010-4655</a></span>, <span style="white-space:nowrap">S.<span style="display:inline-block;width:.2em">&nbsp;</span>203–213</span>, <a href="Digital_Object_Identifier" title="Digital Object Identifier">doi</a>:<span class="uri-handle" style="white-space:nowrap"><a rel="nofollow" class="external text" href="https://doi.org/10.1016/0010-4655%2895%2900114-7">10.1016/0010-4655(95)00114-7</a></span>.<span class="Z3988" title="ctx_ver=Z39.88-2004&amp;rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&amp;rfr_id=info:sid/de.wikipedia.org:Bootstrapping-Verfahren&amp;rft.atitle=The+moving+block+bootstrap+to+assess+the+accuracy+of+statistical+estimates+in+Ising+model+simulations&amp;rft.au=S.+Mignani%2C+R.+Rosa&amp;rft.date=1995-12&amp;rft.doi=10.1016%2F0010-4655%2895%2900114-7&amp;rft.genre=journal&amp;rft.issn=0010-4655&amp;rft.issue=2-3&amp;rft.jtitle=Computer+Physics+Communications&amp;rft.pages=203-213&amp;rft.volume=92" style="display:none">&nbsp;</span></span>
</li>
<li id="cite_note-12"><span class="mw-cite-backlink"><a href="#cite_ref-12">↑</a></span> <span class="reference-text">Bickel, Götze, van Zwet: "Resampling fewer than n observations: gains, losses, and remedies for losses." Statistica Sinica 7 (1997), 1-31</span>
</li>
<li id="cite_note-13"><span class="mw-cite-backlink"><a href="#cite_ref-13">↑</a></span> <span class="reference-text">m-out-of-n Bootstrap Stephen M. S. Lee, <a rel="nofollow" class="external free" href="https://doi.org/10.1002/9781118445112.stat08002">https://doi.org/10.1002/9781118445112.stat08002</a></span>
</li>
<li id="cite_note-14"><span class="mw-cite-backlink"><a href="#cite_ref-14">↑</a></span> <span class="reference-text">Bradley Efron, Robert Tibshirani: <cite style="font-style:italic">An Introduction to the Bootstrap</cite>. CRC Press, 1993, ISBN 978-0-412-04231-7, <span style="white-space:nowrap">S.<span style="display:inline-block;width:.2em">&nbsp;</span>1–6</span>.<span class="Z3988" title="ctx_ver=Z39.88-2004&amp;rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&amp;rfr_id=info:sid/de.wikipedia.org:Bootstrapping-Verfahren&amp;rft.au=Bradley+Efron%2C+Robert+Tibshirani&amp;rft.btitle=An+Introduction+to+the+Bootstrap&amp;rft.date=1993&amp;rft.genre=book&amp;rft.isbn=9780412042317&amp;rft.pages=1-6&amp;rft.pub=CRC+Press" style="display:none">&nbsp;</span></span>
</li>
<li id="cite_note-15"><span class="mw-cite-backlink"><a href="#cite_ref-15">↑</a></span> <span class="reference-text"><a rel="nofollow" class="external free" href="https://books.google.de/books?id=QR36AwAAQBAJ&amp;pg=PA38">https://books.google.de/books?id=QR36AwAAQBAJ&amp;pg=PA38</a></span>
</li>
<li id="cite_note-16"><span class="mw-cite-backlink"><a href="#cite_ref-16">↑</a></span> <span class="reference-text">Freedman, D. A.: <cite style="font-style:italic">Bootstrapping Regression Models</cite>. The Institute of Mathematical Statistics, November 1981.<span class="Z3988" title="ctx_ver=Z39.88-2004&amp;rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&amp;rfr_id=info:sid/de.wikipedia.org:Bootstrapping-Verfahren&amp;rft.au=Freedman%2C+D.+A.&amp;rft.btitle=Bootstrapping+Regression+Models&amp;rft.date=1981-11&amp;rft.genre=book&amp;rft.pub=The+Institute+of+Mathematical+Statistics" style="display:none">&nbsp;</span></span>
</li>
<li id="cite_note-17"><span class="mw-cite-backlink"><a href="#cite_ref-17">↑</a></span> <span class="reference-text">Noureddine El Karoui, Elizabeth Purdom: <cite style="font-style:italic">Can We Trust the Bootstrap in High-dimensions? The Case of Linear Models</cite>. In: <cite style="font-style:italic">Journal of Machine Learning Research</cite>. <span style="white-space:nowrap">Band<span style="display:inline-block;width:.2em">&nbsp;</span>19</span>, <span style="white-space:nowrap">Nr.<span style="display:inline-block;width:.2em">&nbsp;</span>5</span>, 2018, <a href="Internationale_Standardnummer_f%C3%BCr_fortlaufende_Sammelwerke" title="Internationale Standardnummer für fortlaufende Sammelwerke">ISSN</a>&nbsp;<span style="white-space:nowrap"><a rel="nofollow" class="external text" href="https://zdb-katalog.de/list.xhtml?t=iss%3D%221533-7928%22&amp;key=cql">1533-7928</a></span>, <span style="white-space:nowrap">S.<span style="display:inline-block;width:.2em">&nbsp;</span>1–66</span> (<a rel="nofollow" class="external text" href="https://jmlr.org/papers/v19/17-006.html">jmlr.org</a> [abgerufen am 21.&nbsp;Juli 2021]).<span class="Z3988" title="ctx_ver=Z39.88-2004&amp;rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&amp;rfr_id=info:sid/de.wikipedia.org:Bootstrapping-Verfahren&amp;rft.atitle=Can+We+Trust+the+Bootstrap+in+High-dimensions%3F+The+Case+of+Linear+Models&amp;rft.au=Noureddine+El+Karoui%2C+Elizabeth+Purdom&amp;rft.date=2018&amp;rft.genre=journal&amp;rft.issn=1533-7928&amp;rft.issue=5&amp;rft.jtitle=Journal+of+Machine+Learning+Research&amp;rft.pages=1-66&amp;rft.volume=19" style="display:none">&nbsp;</span></span>
</li>
<li id="cite_note-18"><span class="mw-cite-backlink"><a href="#cite_ref-18">↑</a></span> <span class="reference-text">Bradley Efron, Robert Tibshirani: <cite style="font-style:italic">Improvements on Cross-Validation: The 632+ Bootstrap Method</cite>. In: <cite style="font-style:italic">Journal of the American Statistical Association</cite>. <span style="white-space:nowrap">Band<span style="display:inline-block;width:.2em">&nbsp;</span>92</span>, <span style="white-space:nowrap">Nr.<span style="display:inline-block;width:.2em">&nbsp;</span>438</span>, 1.&nbsp;Juni 1997, <a href="Internationale_Standardnummer_f%C3%BCr_fortlaufende_Sammelwerke" title="Internationale Standardnummer für fortlaufende Sammelwerke">ISSN</a>&nbsp;<span style="white-space:nowrap"><a rel="nofollow" class="external text" href="https://zdb-katalog.de/list.xhtml?t=iss%3D%220162-1459%22&amp;key=cql">0162-1459</a></span>, <span style="white-space:nowrap">S.<span style="display:inline-block;width:.2em">&nbsp;</span>548–560</span>, <a href="Digital_Object_Identifier" title="Digital Object Identifier">doi</a>:<span class="uri-handle" style="white-space:nowrap"><a rel="nofollow" class="external text" href="https://doi.org/10.1080/01621459.1997.10474007">10.1080/01621459.1997.10474007</a></span>.<span class="Z3988" title="ctx_ver=Z39.88-2004&amp;rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&amp;rfr_id=info:sid/de.wikipedia.org:Bootstrapping-Verfahren&amp;rft.atitle=Improvements+on+Cross-Validation%3A+The+632%2B+Bootstrap+Method&amp;rft.au=Bradley+Efron%2C+Robert+Tibshirani&amp;rft.date=1997-06-01&amp;rft.doi=10.1080%2F01621459.1997.10474007&amp;rft.genre=journal&amp;rft.issn=0162-1459&amp;rft.issue=438&amp;rft.jtitle=Journal+of+the+American+Statistical+Association&amp;rft.pages=548-560&amp;rft.volume=92" style="display:none">&nbsp;</span></span>
</li>
<li id="cite_note-19"><span class="mw-cite-backlink"><a href="#cite_ref-19">↑</a></span> <span class="reference-text">Jaap Geluk, Laurens de Haan: <cite style="font-style:italic">On bootstrap sample size in extreme value theory</cite>. In: <cite style="font-style:italic">Publications de l'Institut Mathematique</cite>. <span style="white-space:nowrap">Band<span style="display:inline-block;width:.2em">&nbsp;</span>71</span>, <span style="white-space:nowrap">Nr.<span style="display:inline-block;width:.2em">&nbsp;</span>85</span>, 2002, <a href="Internationale_Standardnummer_f%C3%BCr_fortlaufende_Sammelwerke" title="Internationale Standardnummer für fortlaufende Sammelwerke">ISSN</a>&nbsp;<span style="white-space:nowrap"><a rel="nofollow" class="external text" href="https://zdb-katalog.de/list.xhtml?t=iss%3D%220350-1302%22&amp;key=cql">0350-1302</a></span>, <span style="white-space:nowrap">S.<span style="display:inline-block;width:.2em">&nbsp;</span>21–26</span>, <a href="Digital_Object_Identifier" title="Digital Object Identifier">doi</a>:<span class="uri-handle" style="white-space:nowrap"><a rel="nofollow" class="external text" href="https://doi.org/10.2298/pim0271021g">10.2298/pim0271021g</a></span>.<span class="Z3988" title="ctx_ver=Z39.88-2004&amp;rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&amp;rfr_id=info:sid/de.wikipedia.org:Bootstrapping-Verfahren&amp;rft.atitle=On+bootstrap+sample+size+in+extreme+value+theory&amp;rft.au=Jaap+Geluk%2C+Laurens+de+Haan&amp;rft.date=2002&amp;rft.doi=10.2298%2Fpim0271021g&amp;rft.genre=journal&amp;rft.issn=0350-1302&amp;rft.issue=85&amp;rft.jtitle=Publications+de+l%27Institut+Mathematique&amp;rft.pages=21-26&amp;rft.volume=71" style="display:none">&nbsp;</span></span>
</li>
<li id="cite_note-20"><span class="mw-cite-backlink"><a href="#cite_ref-20">↑</a></span> <span class="reference-text">Mashreghi, Zeinab, David Haziza, and Christian Léger. "A survey of bootstrap methods in finite population sampling." (2016): 1-52. <a rel="nofollow" class="external free" href="https://projecteuclid.org/journals/statistics-surveys/volume-10/issue-none/A-survey-of-bootstrap-methods-in-finite-population-sampling/10.1214/16-SS113.full">https://projecteuclid.org/journals/statistics-surveys/volume-10/issue-none/A-survey-of-bootstrap-methods-in-finite-population-sampling/10.1214/16-SS113.full</a></span>
</li>
</ol></div><!--htdig_noindex--><div><div class="zim-footer">
Dieser Artikel wurde von <a class="external text" title="Zuletzt bearbeitet am 2025-12-20" href="https://de.wikipedia.org/wiki/?title=Bootstrapping-Verfahren&amp;oldid=262571714">Wikipedia</a> herausgegeben. Der Text ist unter <a class="external text" href="https://creativecommons.org/licenses/by-sa/4.0/deed.de">Creative Commons Attribution-Share Alike 4.0</a> verfügbar, sofern nicht anders angegeben. Für die Mediendateien können zusätzliche Bedingungen gelten.
</div>
</div><!--/htdig_noindex--></div>
</div>
</main>
</div>
</div>
</div>
<script src="./_webp_/webpHandler.js"></script>

</body></html>