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>Vektorautoregressive Modelle</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/Vektorautoregressive_Modelle"> <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-Vektorautoregressive_Modelle rootpage-Vektorautoregressive_Modelle 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">Vektorautoregressive Modelle</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><b>Vektorautoregressive Modelle</b> (kurz <b>VAR-Modelle</b>) sind sehr weit verbreitete <a href="%C3%96konometrie" title="Ökonometrie">ökonometrische</a> Modelle zum simultanen Schätzen mehrerer Gleichungen. Sie sind das mehrdimensionale Analogon zum <a href="ARMA-Modell" title="ARMA-Modell">autoregressiven Modell</a>. Sie gehören zu der Modelloberklasse der VARMA-Modelle. Bei dieser Art von <a href="Zeitreihen" class="mw-redirect" title="Zeitreihen">Zeitreihenmodellen</a> werden die <a href="Exogene_und_endogene_Variable" title="Exogene und endogene Variable">endogenen Variablen</a> sowohl durch ihre eigenen Vergangenheitswerte, als auch durch die Vergangenheitswerte der anderen endogenen Variablen bestimmt. Die Variablen werden deshalb auch als <a href="Exogene_und_endogene_Variable#Verzögerte_exogene_und_endogene_Variable" title="Exogene und endogene Variable">verzögert exogen</a> bezeichnet. Es gibt also eine <a href="R%C3%BCckkopplung" title="Rückkopplung">Rückkopplung</a> zwischen den Variablen, wenn die <a href="Kovarianzmatrix" title="Kovarianzmatrix">Kovarianzmatrix</a> nicht-diagonal ist.
</p>

<div class="mw-heading mw-heading2"><h2 id="Motivation">Motivation</h2></div>
<p>Ein einfaches zweidimensionales VAR-Modell enthält zwei Zeitreihen <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_{t}^{(1)}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msubsup>
<mi>x</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mo stretchy="false">(</mo>
<mn>1</mn>
<mo stretchy="false">)</mo>
</mrow>
</msubsup>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle x_{t}^{(1)}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/31e379cac0a18a5e9b7647c6ebe84abf8de54a2c.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -1.005ex; width:3.663ex; height:3.676ex;" alt="{\displaystyle x_{t}^{(1)}}" 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 x_{t}^{(2)}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msubsup>
<mi>x</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mo stretchy="false">(</mo>
<mn>2</mn>
<mo stretchy="false">)</mo>
</mrow>
</msubsup>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle x_{t}^{(2)}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/81cff831c197b66ddc60798ecd96f60145d8df1d.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -1.005ex; width:3.663ex; height:3.676ex;" alt="{\displaystyle x_{t}^{(2)}}" loading="lazy"></span>, die erklärt werden, und noch eine weitere Zeitreihe <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 z_{t}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msub>
<mi>z</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
</mrow>
</msub>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle z_{t}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/e396fb172660aa223e35c928e2e6985f511d8cc6.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.671ex; width:1.907ex; height:2.009ex;" alt="{\displaystyle z_{t}}" loading="lazy"></span>, die zur Erklärung herangezogen wird. Die Modellgleichungen lauten dann
</p>
<dl><dd><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_{t}^{(1)}=\nu _{1}+a_{11}x_{t-1}^{(1)}+a_{12}x_{t-1}^{(2)}+b_{1}z_{t}+\epsilon _{t}^{(1)}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msubsup>
<mi>x</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mo stretchy="false">(</mo>
<mn>1</mn>
<mo stretchy="false">)</mo>
</mrow>
</msubsup>
<mo>=</mo>
<msub>
<mi>ν<!-- ν --></mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>1</mn>
</mrow>
</msub>
<mo>+</mo>
<msub>
<mi>a</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>11</mn>
</mrow>
</msub>
<msubsup>
<mi>x</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
<mo>−<!-- − --></mo>
<mn>1</mn>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mo stretchy="false">(</mo>
<mn>1</mn>
<mo stretchy="false">)</mo>
</mrow>
</msubsup>
<mo>+</mo>
<msub>
<mi>a</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>12</mn>
</mrow>
</msub>
<msubsup>
<mi>x</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
<mo>−<!-- − --></mo>
<mn>1</mn>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mo stretchy="false">(</mo>
<mn>2</mn>
<mo stretchy="false">)</mo>
</mrow>
</msubsup>
<mo>+</mo>
<msub>
<mi>b</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>1</mn>
</mrow>
</msub>
<msub>
<mi>z</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
</mrow>
</msub>
<mo>+</mo>
<msubsup>
<mi>ϵ<!-- ϵ --></mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mo stretchy="false">(</mo>
<mn>1</mn>
<mo stretchy="false">)</mo>
</mrow>
</msubsup>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle x_{t}^{(1)}=\nu _{1}+a_{11}x_{t-1}^{(1)}+a_{12}x_{t-1}^{(2)}+b_{1}z_{t}+\epsilon _{t}^{(1)}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/7ea2de3dfd7fe1e438ae311ca76aa04106c8c951.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -1.171ex; width:42.287ex; height:3.843ex;" alt="{\displaystyle x_{t}^{(1)}=\nu _{1}+a_{11}x_{t-1}^{(1)}+a_{12}x_{t-1}^{(2)}+b_{1}z_{t}+\epsilon _{t}^{(1)}}" loading="lazy"></span>,</dd>
<dd><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_{t}^{(2)}=\nu _{2}+a_{21}x_{t-1}^{(1)}+a_{22}x_{t-1}^{(2)}+b_{2}z_{t}+\epsilon _{t}^{(2)}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msubsup>
<mi>x</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mo stretchy="false">(</mo>
<mn>2</mn>
<mo stretchy="false">)</mo>
</mrow>
</msubsup>
<mo>=</mo>
<msub>
<mi>ν<!-- ν --></mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>2</mn>
</mrow>
</msub>
<mo>+</mo>
<msub>
<mi>a</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>21</mn>
</mrow>
</msub>
<msubsup>
<mi>x</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
<mo>−<!-- − --></mo>
<mn>1</mn>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mo stretchy="false">(</mo>
<mn>1</mn>
<mo stretchy="false">)</mo>
</mrow>
</msubsup>
<mo>+</mo>
<msub>
<mi>a</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>22</mn>
</mrow>
</msub>
<msubsup>
<mi>x</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
<mo>−<!-- − --></mo>
<mn>1</mn>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mo stretchy="false">(</mo>
<mn>2</mn>
<mo stretchy="false">)</mo>
</mrow>
</msubsup>
<mo>+</mo>
<msub>
<mi>b</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>2</mn>
</mrow>
</msub>
<msub>
<mi>z</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
</mrow>
</msub>
<mo>+</mo>
<msubsup>
<mi>ϵ<!-- ϵ --></mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mo stretchy="false">(</mo>
<mn>2</mn>
<mo stretchy="false">)</mo>
</mrow>
</msubsup>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle x_{t}^{(2)}=\nu _{2}+a_{21}x_{t-1}^{(1)}+a_{22}x_{t-1}^{(2)}+b_{2}z_{t}+\epsilon _{t}^{(2)}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/235972ae1e89a73f6422bdfa3d2ed0554bc69634.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -1.171ex; width:42.287ex; height:3.843ex;" alt="{\displaystyle x_{t}^{(2)}=\nu _{2}+a_{21}x_{t-1}^{(1)}+a_{22}x_{t-1}^{(2)}+b_{2}z_{t}+\epsilon _{t}^{(2)}}" loading="lazy"></span>.</dd>
<dd>oder in Matrixschreibweise:</dd>
<dd><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_{t}=\nu +A_{1}\cdot X_{t-1}+B\cdot Z_{t}+\epsilon _{t}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msub>
<mi>X</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
</mrow>
</msub>
<mo>=</mo>
<mi>ν<!-- ν --></mi>
<mo>+</mo>
<msub>
<mi>A</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>1</mn>
</mrow>
</msub>
<mo>⋅<!-- ⋅ --></mo>
<msub>
<mi>X</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
<mo>−<!-- − --></mo>
<mn>1</mn>
</mrow>
</msub>
<mo>+</mo>
<mi>B</mi>
<mo>⋅<!-- ⋅ --></mo>
<msub>
<mi>Z</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
</mrow>
</msub>
<mo>+</mo>
<msub>
<mi>ϵ<!-- ϵ --></mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
</mrow>
</msub>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle X_{t}=\nu +A_{1}\cdot X_{t-1}+B\cdot Z_{t}+\epsilon _{t}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/a3ae81ce77b4c9c87368d28593779bededc762c4.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.671ex; width:32.556ex; height:2.509ex;" alt="{\displaystyle X_{t}=\nu +A_{1}\cdot X_{t-1}+B\cdot Z_{t}+\epsilon _{t}}" loading="lazy"></span></dd></dl>
<p>Die Werte der beiden Zeitreihen <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_{t}^{(1)}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msubsup>
<mi>x</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mo stretchy="false">(</mo>
<mn>1</mn>
<mo stretchy="false">)</mo>
</mrow>
</msubsup>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle x_{t}^{(1)}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/31e379cac0a18a5e9b7647c6ebe84abf8de54a2c.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -1.005ex; width:3.663ex; height:3.676ex;" alt="{\displaystyle x_{t}^{(1)}}" 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 x_{t}^{(2)}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msubsup>
<mi>x</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mo stretchy="false">(</mo>
<mn>2</mn>
<mo stretchy="false">)</mo>
</mrow>
</msubsup>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle x_{t}^{(2)}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/81cff831c197b66ddc60798ecd96f60145d8df1d.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -1.005ex; width:3.663ex; height:3.676ex;" alt="{\displaystyle x_{t}^{(2)}}" loading="lazy"></span> zur Zeit <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_/eb734a37dd21ce173a46342d1cc64c92/65658b7b223af9e1acc877d848888ecdb4466560.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.338ex; width:0.84ex; height:2.009ex;" alt="{\displaystyle t}" loading="lazy"></span> hängen also ab von
</p>
<ul><li>der Vergangenheit <i>beider</i> Zeitreihen,
<ul><li>im VAR(1)-Modell nur von den Werten der Vorperiode, <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_{t-1}^{(1)}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msubsup>
<mi>x</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
<mo>−<!-- − --></mo>
<mn>1</mn>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mo stretchy="false">(</mo>
<mn>1</mn>
<mo stretchy="false">)</mo>
</mrow>
</msubsup>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle x_{t-1}^{(1)}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/1d76765bbb97d87711f7b068e01e7836aefe1d33.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -1.171ex; width:4.256ex; height:3.843ex;" alt="{\displaystyle x_{t-1}^{(1)}}" 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 x_{t-1}^{(2)}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msubsup>
<mi>x</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
<mo>−<!-- − --></mo>
<mn>1</mn>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mo stretchy="false">(</mo>
<mn>2</mn>
<mo stretchy="false">)</mo>
</mrow>
</msubsup>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle x_{t-1}^{(2)}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/9cd9a35a96a5352e771c60632c2f224245fffc93.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -1.171ex; width:4.256ex; height:3.843ex;" alt="{\displaystyle x_{t-1}^{(2)}}" loading="lazy"></span>,</li>
<li>im VAR(p)-Modell können weitere <i>lags</i> (von englisch „Verzögerungen“) miteinbezogen werden,</li></ul></li>
<li>weiteren erklärenden Zeitreihen, hier: <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 z_{t}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msub>
<mi>z</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
</mrow>
</msub>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle z_{t}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/e396fb172660aa223e35c928e2e6985f511d8cc6.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.671ex; width:1.907ex; height:2.009ex;" alt="{\displaystyle z_{t}}" loading="lazy"></span> zur Zeit <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_/eb734a37dd21ce173a46342d1cc64c92/65658b7b223af9e1acc877d848888ecdb4466560.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.338ex; width:0.84ex; height:2.009ex;" alt="{\displaystyle t}" loading="lazy"></span> sowie</li>
<li>den <a href="Fehlerterm" class="mw-redirect" title="Fehlerterm">Fehlertermen</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 \epsilon _{i}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msub>
<mi>ϵ<!-- ϵ --></mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>i</mi>
</mrow>
</msub>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle \epsilon _{i}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/9be3140164b763359077d92b2cd33798eb6a488c.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.671ex; width:1.744ex; height:2.009ex;" alt="{\displaystyle \epsilon _{i}}" loading="lazy"></span>.</li></ul>
<p>Im Modell müssen die Modellparameter
</p>
<ul><li><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 \nu ={\begin{pmatrix}\nu _{1}\\\nu _{2}\end{pmatrix}}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>ν<!-- ν --></mi>
<mo>=</mo>
<mrow class="MJX-TeXAtom-ORD">
<mrow>
<mo>(</mo>
<mtable rowspacing="4pt" columnspacing="1em">
<mtr>
<mtd>
<msub>
<mi>ν<!-- ν --></mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>1</mn>
</mrow>
</msub>
</mtd>
</mtr>
<mtr>
<mtd>
<msub>
<mi>ν<!-- ν --></mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>2</mn>
</mrow>
</msub>
</mtd>
</mtr>
</mtable>
<mo>)</mo>
</mrow>
</mrow>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle \nu ={\begin{pmatrix}\nu _{1}\\\nu _{2}\end{pmatrix}}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/b17c6cd07df4ab3b3422b416f35ca0434363030e.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -2.505ex; width:10.706ex; height:6.176ex;" alt="{\displaystyle \nu ={\begin{pmatrix}\nu _{1}\\\nu _{2}\end{pmatrix}}}" loading="lazy"></span>,</li>
<li><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 A_{1}={\begin{pmatrix}a_{11}&amp;a_{12}\\a_{21}&amp;a_{22}\end{pmatrix}}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msub>
<mi>A</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>1</mn>
</mrow>
</msub>
<mo>=</mo>
<mrow class="MJX-TeXAtom-ORD">
<mrow>
<mo>(</mo>
<mtable rowspacing="4pt" columnspacing="1em">
<mtr>
<mtd>
<msub>
<mi>a</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>11</mn>
</mrow>
</msub>
</mtd>
<mtd>
<msub>
<mi>a</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>12</mn>
</mrow>
</msub>
</mtd>
</mtr>
<mtr>
<mtd>
<msub>
<mi>a</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>21</mn>
</mrow>
</msub>
</mtd>
<mtd>
<msub>
<mi>a</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>22</mn>
</mrow>
</msub>
</mtd>
</mtr>
</mtable>
<mo>)</mo>
</mrow>
</mrow>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle A_{1}={\begin{pmatrix}a_{11}&amp;a_{12}\\a_{21}&amp;a_{22}\end{pmatrix}}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/96c550117745c62366c5b7d0c3e2da4a86e8d186.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -2.505ex; width:18.603ex; height:6.176ex;" alt="{\displaystyle A_{1}={\begin{pmatrix}a_{11}&amp;a_{12}\\a_{21}&amp;a_{22}\end{pmatrix}}}" loading="lazy"></span> und</li>
<li><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={\begin{pmatrix}b_{1}\\b_{2}\end{pmatrix}}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>B</mi>
<mo>=</mo>
<mrow class="MJX-TeXAtom-ORD">
<mrow>
<mo>(</mo>
<mtable rowspacing="4pt" columnspacing="1em">
<mtr>
<mtd>
<msub>
<mi>b</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>1</mn>
</mrow>
</msub>
</mtd>
</mtr>
<mtr>
<mtd>
<msub>
<mi>b</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>2</mn>
</mrow>
</msub>
</mtd>
</mtr>
</mtable>
<mo>)</mo>
</mrow>
</mrow>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle B={\begin{pmatrix}b_{1}\\b_{2}\end{pmatrix}}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/f19817ae3bbacbf5b8903931f150a1e57d19c966.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -2.505ex; width:11.087ex; height:6.176ex;" alt="{\displaystyle B={\begin{pmatrix}b_{1}\\b_{2}\end{pmatrix}}}" loading="lazy"></span></li></ul>
<p>iterativ aus den Daten geschätzt werden.
</p>
<div class="mw-heading mw-heading2"><h2 id="Abgrenzung_zu_Transferfunktionsmodellen">Abgrenzung zu Transferfunktionsmodellen</h2></div>
<p>Es gibt Ähnlichkeiten zwischen den VAR-Modellen und den <a href="Transferfunktionsmodell" title="Transferfunktionsmodell">Transferfunktionsmodellen</a>. Ein VAR(1)-Modell darf aber nicht als <a href="Kausal" class="mw-redirect" title="Kausal">kausales</a> Transferfunktionsmodell angesehen werden. Grund ist die jeweilige <a href="Kontempor%C3%A4r" class="mw-redirect" title="Kontemporär">kontemporäre</a> Korrelierung der Schockvariablen. Durch die <a href="Orthogonalisierung" class="mw-redirect" title="Orthogonalisierung">Orthogonalisierung</a> der Schockvariablen (<a href="Diagonalmatrix" title="Diagonalmatrix">Diagonalisierung</a> der <a href="Kovarianzmatrix" title="Kovarianzmatrix">Kovarianzmatrix</a>) kann ein VAR(1)-Modell trotzdem in ein kausales Transferfunktionsmodell umgewandelt werden.
</p>
<div class="mw-heading mw-heading2"><h2 id="Spezifikation_und_Schätzung_von_VAR-Modellen"><span id="Spezifikation_und_Sch.C3.A4tzung_von_VAR-Modellen"></span>Spezifikation und Schätzung von VAR-Modellen</h2></div>
<p>In <a href="Matrix_(Mathematik)" title="Matrix (Mathematik)">Vektor-Matrix-Form</a> kann ein <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>-dimensionales VAR(p)-Modell geschrieben werden als
</p>
<dl><dd><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_{t}=\nu +A_{1}\cdot X_{t-1}+A_{2}\cdot X_{t-2}+\ldots +A_{p}\cdot X_{t-p}+B\cdot Z_{t}+\epsilon _{t}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msub>
<mi>X</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
</mrow>
</msub>
<mo>=</mo>
<mi>ν<!-- ν --></mi>
<mo>+</mo>
<msub>
<mi>A</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>1</mn>
</mrow>
</msub>
<mo>⋅<!-- ⋅ --></mo>
<msub>
<mi>X</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
<mo>−<!-- − --></mo>
<mn>1</mn>
</mrow>
</msub>
<mo>+</mo>
<msub>
<mi>A</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>2</mn>
</mrow>
</msub>
<mo>⋅<!-- ⋅ --></mo>
<msub>
<mi>X</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
<mo>−<!-- − --></mo>
<mn>2</mn>
</mrow>
</msub>
<mo>+</mo>
<mo>…<!-- … --></mo>
<mo>+</mo>
<msub>
<mi>A</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>p</mi>
</mrow>
</msub>
<mo>⋅<!-- ⋅ --></mo>
<msub>
<mi>X</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
<mo>−<!-- − --></mo>
<mi>p</mi>
</mrow>
</msub>
<mo>+</mo>
<mi>B</mi>
<mo>⋅<!-- ⋅ --></mo>
<msub>
<mi>Z</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
</mrow>
</msub>
<mo>+</mo>
<msub>
<mi>ϵ<!-- ϵ --></mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
</mrow>
</msub>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle X_{t}=\nu +A_{1}\cdot X_{t-1}+A_{2}\cdot X_{t-2}+\ldots +A_{p}\cdot X_{t-p}+B\cdot Z_{t}+\epsilon _{t}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/2c76de42f1048a5cc94e494cb7215532b205c3e7.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -1.005ex; width:62.465ex; height:2.843ex;" alt="{\displaystyle X_{t}=\nu +A_{1}\cdot X_{t-1}+A_{2}\cdot X_{t-2}+\ldots +A_{p}\cdot X_{t-p}+B\cdot Z_{t}+\epsilon _{t}}" loading="lazy"></span>,</dd></dl>
<p>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_{t}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msub>
<mi>X</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
</mrow>
</msub>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle X_{t}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/82120d04dfb3cbadc4912951dd12b5568c9cd8f3.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.671ex; width:2.75ex; height:2.509ex;" alt="{\displaystyle X_{t}}" loading="lazy"></span> den Vektor der endogenen Variablen, <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 Z_{t}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msub>
<mi>Z</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
</mrow>
</msub>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle Z_{t}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/a4494df739b00ddebb3f741b5a5aab7415a78736.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.671ex; width:2.413ex; height:2.509ex;" alt="{\displaystyle Z_{t}}" loading="lazy"></span> den Vektor der exogenen Variablen 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 \epsilon _{t}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msub>
<mi>ϵ<!-- ϵ --></mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
</mrow>
</msub>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle \epsilon _{t}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/f1ff4ca7b5c076264ecd5bbc087863a23c4dfb9a.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.671ex; width:1.77ex; height:2.009ex;" alt="{\displaystyle \epsilon _{t}}" loading="lazy"></span> den Fehlerterm bezeichnet. Die Vektoren <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 \nu ,B\in \mathbb {R} ^{n}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<mi>ν<!-- ν --></mi>
<mo>,</mo>
<mi>B</mi>
<mo>∈<!-- ∈ --></mo>
<msup>
<mrow class="MJX-TeXAtom-ORD">
<mi mathvariant="double-struck">R</mi>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mi>n</mi>
</mrow>
</msup>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle \nu ,B\in \mathbb {R} ^{n}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/a94db8a37c5aba478f36cba38c7ff180e531bc0a.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.671ex; width:9.767ex; height:2.676ex;" alt="{\displaystyle \nu ,B\in \mathbb {R} ^{n}}" loading="lazy"></span> und die Matrizen <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 A_{1},\dotsc ,A_{p}\in \mathbb {R} ^{n\times n}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msub>
<mi>A</mi>
<mrow class="MJX-TeXAtom-ORD">
<mn>1</mn>
</mrow>
</msub>
<mo>,</mo>
<mo>…<!-- … --></mo>
<mo>,</mo>
<msub>
<mi>A</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>p</mi>
</mrow>
</msub>
<mo>∈<!-- ∈ --></mo>
<msup>
<mrow class="MJX-TeXAtom-ORD">
<mi mathvariant="double-struck">R</mi>
</mrow>
<mrow class="MJX-TeXAtom-ORD">
<mi>n</mi>
<mo>×<!-- × --></mo>
<mi>n</mi>
</mrow>
</msup>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle A_{1},\dotsc ,A_{p}\in \mathbb {R} ^{n\times n}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/05fa27fb39a3e0ed445280d065676d5b46072b8b.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -1.005ex; width:18.78ex; height:3.009ex;" alt="{\displaystyle A_{1},\dotsc ,A_{p}\in \mathbb {R} ^{n\times n}}" loading="lazy"></span> sollen geschätzt werden. Dies ist ein lineares Modell, somit findet der <a href="Satz_von_Gau%C3%9F-Markow" title="Satz von Gauß-Markow">Satz von Gauß-Markow</a> Anwendung und das Modell kann effizient mit der <a href="Methode_der_kleinsten_Quadrate" title="Methode der kleinsten Quadrate">Methode der kleinsten Quadrate</a> geschätzt werden. Zur Herleitung des Schätzers, der Kovarianzmatrix usw. siehe z.&nbsp;B. Lütkepohl (1991).<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>
</p><p>Zur Wahl der optimalen Anzahl <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> von Verzögerungen (optimale Lagordnung) können z.&nbsp;B. das Akaike- oder das Schwarz-<a href="Informationskriterium" title="Informationskriterium">Informationskriterium</a> herangezogen werden. Auch wenn die Kleinste Quadrate Schätzung selbst keinerlei Voraussetzungen seitens Erwartungswert oder Varianz 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_{t}}">
<semantics>
<mrow class="MJX-TeXAtom-ORD">
<mstyle displaystyle="true" scriptlevel="0">
<msub>
<mi>X</mi>
<mrow class="MJX-TeXAtom-ORD">
<mi>t</mi>
</mrow>
</msub>
</mstyle>
</mrow>
<annotation encoding="application/x-tex">{\displaystyle X_{t}}</annotation>
</semantics>
</math></span><img src="./_assets_/eb734a37dd21ce173a46342d1cc64c92/82120d04dfb3cbadc4912951dd12b5568c9cd8f3.svg" class="mwe-math-fallback-image-inline mw-invert skin-invert" aria-hidden="true" style="vertical-align: -0.671ex; width:2.75ex; height:2.509ex;" alt="{\displaystyle X_{t}}" loading="lazy"></span>hat, sind konstante <a href="Moment_(Stochastik)" title="Moment (Stochastik)">Momente</a> doch für Güteaussagen und die <a href="Spezifikation_(Statistik)" title="Spezifikation (Statistik)">Spezifikation</a> der Lags über die Informationskriterien erforderlich. Daher werden Zeitreihen vor der Schätzung von VAR Modellen üblicherweise trendbereinigt (etwa mit <a href="Hodrick-Prescott-Filter" title="Hodrick-Prescott-Filter">Hodrick-Prescott-Filter</a>) und dadurch <a href="Station%C3%A4rer_stochastischer_Prozess" title="Stationärer stochastischer Prozess">stationär</a> gemacht. Ein alternativer Ansatz ist die Schätzung von Vektor-Fehlerkorrekturmodellen.
</p>
<div class="mw-heading mw-heading2"><h2 id="Vorzüge_und_Probleme_von_VAR"><span id="Vorz.C3.BCge_und_Probleme_von_VAR"></span>Vorzüge und Probleme von VAR</h2></div>
<div class="mw-heading mw-heading3"><h3 id="Vorzüge"><span id="Vorz.C3.BCge"></span>Vorzüge</h3></div>
<p>VAR-Modelle verdanken ihre heutige Popularität in den Wirtschaftswissenschaften wesentlich der tiefgreifenden Kritik von <a href="Christopher_Sims" title="Christopher Sims">Christopher Sims</a> (1980)<sup id="cite_ref-2" class="reference"><a href="#cite_note-2"><span class="cite-bracket">[</span>2<span class="cite-bracket">]</span></a></sup> an theoriefundierten Mehrgleichungsmodellen, die in den 1960 und 1970er Jahren für ökonomische Prognosen eingesetzt wurden, Sims nimmt z.&nbsp;B. auf das FRB-MIT Modell<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> Bezug. Diese Modelle bestanden aus bis zu mehreren Dutzend Gleichungen, die einzelne Sektoren der Ökonomie beschrieben und separat geschätzt wurden. Die Modellgleichungen setzten i.&nbsp;d.&nbsp;R. nur einige der endogenen Variablen des Gesamtmodells in Beziehung. Sims kritisiert, dass dies gleichbedeutend mit einer großen Menge mehr oder weniger willkürlicher Restriktionen im Modell ist, die Modellergebnisse massiv verzerren können. Des Weiteren sind solche Modelle erheblich von der <a href="Lucas-Kritik" title="Lucas-Kritik">Lucas-Kritik</a> betroffen und leiden potenziell noch unter zusätzlichen statistischen Problemen.
</p><p>VAR-Modelle sind theoriefrei und setzen daher keinerlei mehr oder weniger willkürliche Restriktionen. Sie sind daher, trotz ihrer relativen Einfachheit, klassischen Mehrgleichungsmodellen prognostisch überlegen und werden bis heute als Benchmark genutzt, um die Prognosegüte moderner theoriebasierter Modelle (insb. <a href="DSGE-Modelle" class="mw-redirect" title="DSGE-Modelle">DSGE-Modelle</a>) zu bewerten.<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>Des Weiteren gibt es mit Structural VARs, das sind VARs mit Restriktionen in der Kovarianzmatrix oder Parametern<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>, Möglichkeiten Vorinformationen gezielt zur Verbesserung der Prognosegüte oder zur Ableitung struktureller dynamischer Aussagen aus VARs zu verwenden.
</p>
<div class="mw-heading mw-heading3"><h3 id="Probleme">Probleme</h3></div>
<ul><li>VAR-Modelle sind durch die vielen zu schätzenden Parameter bei üblichen ökonomischen Datensatzgrößen relativ ungenau, darauf weist bereits Sims (1980) hin.</li>
<li>VAR-Modelle sind nicht zwingend eindeutig, d.&nbsp;h. auch mit Hilfe von Restriktionen kann es unmöglich sein, aus einem SVAR ökonomische Aussagen abzuleiten.<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></li>
<li>VAR-Modelle sind nicht frei von der <a href="Lucas-Kritik" title="Lucas-Kritik">Lucas-Kritik</a>, d.&nbsp;h. sie können nicht ohne weiteres für Politiksimulationen eingesetzt werden.<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></li></ul>
<div class="mw-heading mw-heading2"><h2 id="Literatur">Literatur</h2></div>
<ul><li>Damodar N. Gujarati, Dawn C. Porter: <cite class="lang" lang="en" dir="auto" style="font-style:italic">Basic Econometrics</cite>. 5. Auflage. McGraw-Hill, New York 2009, ISBN 978-0-07-127625-2, <span style="white-space:nowrap">S.<span style="display:inline-block;width:.2em">&nbsp;</span>784–790</span> (englisch).<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:Vektorautoregressive+Modelle&amp;rft.au=Damodar+N.+Gujarati%2C+Dawn+C.+Porter&amp;rft.btitle=Basic+Econometrics&amp;rft.date=2009&amp;rft.edition=5.&amp;rft.genre=book&amp;rft.isbn=9780071276252&amp;rft.pages=784-790&amp;rft.place=New+York&amp;rft.pub=McGraw-Hill" style="display:none">&nbsp;</span></li>
<li><a href="Helmut_L%C3%BCtkepohl" title="Helmut Lütkepohl">Helmut Lütkepohl</a>: <cite style="font-style:italic">New Introduction to Multiple Time Series Analysis Econometrics</cite>. Springer, Berlin / Heidelberg / New York 2005, ISBN 3-540-40172-5, <span style="white-space:nowrap">Teil I <i>Finite Order Vector Autoregressive Processes</i>, S. 13–352</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:Vektorautoregressive+Modelle&amp;rft.au=Helmut+L%C3%BCtkepohl&amp;rft.btitle=New+Introduction+to+Multiple+Time+Series+Analysis+Econometrics&amp;rft.date=2005&amp;rft.genre=book&amp;rft.isbn=3540401725&amp;rft.place=Berlin+%2F+Heidelberg+%2F+New+York&amp;rft.pub=Springer" style="display:none">&nbsp;</span></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">Helmut Lütkepohl: <cite style="font-style:italic">Introduction to Multiple Time Series Analysis</cite>. 1991, <span style="white-space:nowrap">S.<span style="display:inline-block;width:.2em">&nbsp;</span>63<span style="display:inline-block;width:.2em">&nbsp;</span>ff</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/10.1007/978-3-662-02691-5">10.1007/978-3-662-02691-5</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:Vektorautoregressive+Modelle&amp;rft.au=Helmut+L%C3%BCtkepohl&amp;rft.btitle=Introduction+to+Multiple+Time+Series+Analysis&amp;rft.date=1991&amp;rft.doi=10.1007%2F978-3-662-02691-5&amp;rft.genre=book&amp;rft.pages=63ff" style="display:none">&nbsp;</span></span>
</li>
<li id="cite_note-2"><span class="mw-cite-backlink"><a href="#cite_ref-2">↑</a></span> <span class="reference-text">Christopher A. Sims: <cite style="font-style:italic">Macroeconomics and Reality</cite>. In: <cite style="font-style:italic">Econometrica</cite>. <span style="white-space:nowrap">Band<span style="display:inline-block;width:.2em">&nbsp;</span>48</span>, <span style="white-space:nowrap">Nr.<span style="display:inline-block;width:.2em">&nbsp;</span>1</span>, 1980, <span style="white-space:nowrap">S.<span style="display:inline-block;width:.2em">&nbsp;</span>1–48</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/10.2307/1912017">10.2307/1912017</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:Vektorautoregressive+Modelle&amp;rft.atitle=Macroeconomics+and+Reality&amp;rft.au=Christopher+A.+Sims&amp;rft.date=1980&amp;rft.doi=10.2307%2F1912017&amp;rft.genre=journal&amp;rft.issue=1&amp;rft.jtitle=Econometrica&amp;rft.pages=1-48&amp;rft.volume=48" 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">Ando, Albert; Modigliani, Franco; Rasche, Robert: <cite style="font-style:italic">Appendix To Part 1: Equations and Definitions af Variables for the FRB-MIT-Penn Econometric Model</cite>. In: Hickman, Bert G. (Hrsg.): <cite style="font-style:italic">Econo- metric Models of Cyclical Behavior</cite>. NBER, November 1969, <span style="white-space:nowrap">S.<span style="display:inline-block;width:.2em">&nbsp;</span>543–598</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:Vektorautoregressive+Modelle&amp;rft.atitle=Appendix+To+Part+1%3A+Equations+and+Definitions+af+Variables+for+the+FRB-MIT-Penn+Econometric+Model&amp;rft.au=Ando%2C+Albert%3B+Modigliani%2C+Franco%3B+Rasche%2C+...&amp;rft.btitle=Econo-+metric+Models+of+Cyclical+Behavior&amp;rft.date=1969-11&amp;rft.genre=book&amp;rft.pages=543-598&amp;rft.pub=NBER" 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">Negro, Marco Del: <cite style="font-style:italic">On the Fit of New Keynesian Models</cite>. In: <cite style="font-style:italic">Journal of Business and Economic Statistics</cite>. <span style="white-space:nowrap">Band<span style="display:inline-block;width:.2em">&nbsp;</span>2</span>, April 2007, <span style="white-space:nowrap">S.<span style="display:inline-block;width:.2em">&nbsp;</span>123–143</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:Vektorautoregressive+Modelle&amp;rft.atitle=On+the+Fit+of+New+Keynesian+Models&amp;rft.au=Negro%2C+Marco+Del&amp;rft.btitle=Journal+of+Business+and+Economic+Statistics&amp;rft.date=2007-04&amp;rft.genre=book&amp;rft.pages=123-143&amp;rft.volume=2" 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">Helmut Lütkepohl: <cite style="font-style:italic">New Introduction to Multiple Time Series Analysis</cite>. 2005, <span style="white-space:nowrap">S.<span style="display:inline-block;width:.2em">&nbsp;</span>359</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/10.1007/978-3-540-27752-1">10.1007/978-3-540-27752-1</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:Vektorautoregressive+Modelle&amp;rft.au=Helmut+L%C3%BCtkepohl&amp;rft.btitle=New+Introduction+to+Multiple+Time+Series+Analysis&amp;rft.date=2005&amp;rft.doi=10.1007%2F978-3-540-27752-1&amp;rft.genre=book&amp;rft.pages=359" 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">V. V. Chari, Patrick J. Kehoe, Ellen R. McGrattan: <cite style="font-style:italic">A critique of structural VARs using business cycle theory</cite>. 2005 (<a rel="nofollow" class="external text" href="https://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.141.6583">psu.edu</a> [abgerufen am 23.&nbsp;Juli 2018]).<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:Vektorautoregressive+Modelle&amp;rft.au=V.+V.+Chari%2C+Patrick+J.+Kehoe%2C+Ellen+R.+McGrattan&amp;rft.btitle=A+critique+of+structural+VARs+using+business+cycle+theory&amp;rft.date=2005&amp;rft.genre=book" style="display:none">&nbsp;</span></span>
</li>
<li id="cite_note-7"><span class="mw-cite-backlink"><a href="#cite_ref-7">↑</a></span> <span class="reference-text"><cite style="font-style:italic">Handbook of Applied Econometrics. Volume I: Macroeconomics</cite>. In: <cite style="font-style:italic">Handbook of Applied Econometrics</cite>. Volume I: Macroeconomics. Blackwell Publishing Ltd, Oxford, UK 1999, ISBN 0-631-21558-1, <span style="white-space:nowrap">S.<span style="display:inline-block;width:.2em">&nbsp;</span>105<span style="display:inline-block;width:.2em">&nbsp;</span>ff</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/10.1111/b.9780631215585.1999.00003.x">10.1111/b.9780631215585.1999.00003.x</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:Vektorautoregressive+Modelle&amp;rft.atitle=Handbook+of+Applied+Econometrics.+Volume+I%3A+Macroeconomics&amp;rft.btitle=Handbook+of+Applied+Econometrics&amp;rft.date=1999&amp;rft.doi=10.1111%2Fb.9780631215585.1999.00003.x&amp;rft.genre=book&amp;rft.isbn=0631215581&amp;rft.pages=105+ff.&amp;rft.place=Oxford%2C+UK&amp;rft.pub=Blackwell+Publishing+Ltd&amp;rft.volume=Volume+I%3A+Macroeconomics" style="display:none">&nbsp;</span></span>
</li>
</ol></div><!--htdig_noindex--><div><div class="zim-footer">
Dieser Artikel wurde von <a class="external text" title="Zuletzt bearbeitet am 2025-03-08" href="https://de.wikipedia.org/wiki/?title=Vektorautoregressive_Modelle&amp;oldid=254002802">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>