csharpfftfsharpintegrationinterpolationlinear-algebramathdifferentiationmatrixnumericsrandomregressionstatisticsmathnet
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
494 lines
26 KiB
494 lines
26 KiB
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Frameset//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-frameset.dtd">
|
|
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
|
|
<head>
|
|
<title>MultipleRegression - Math.NET Numerics Documentation</title>
|
|
<meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>
|
|
<link type="text/css" rel="stylesheet" href="../main.css"/>
|
|
<script type="text/javascript" src="../js/jquery-1.3.2.min.js"></script>
|
|
<script type="text/javascript" src="../js/jquery.scrollTo-min.js"></script>
|
|
<script type="text/javascript" src="../js/navigation.js"></script>
|
|
<script type="text/javascript" src="../js/example.js"></script>
|
|
</head>
|
|
<body><div id="namespaces">
|
|
<h2 class="fixed">Namespaces</h2>
|
|
<div class="scroll">
|
|
<ul>
|
|
<li>
|
|
<a href="../MathNet.Numerics/index.htm">MathNet.Numerics</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.Differentiation/index.htm">MathNet.Numerics.Differentiation</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.Distributions/index.htm">MathNet.Numerics.Distributions</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.Financial/index.htm">MathNet.Numerics.Financial</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.IntegralTransforms/index.htm">MathNet.Numerics.IntegralTransforms</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.Integration/index.htm">MathNet.Numerics.Integration</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.Interpolation/index.htm">MathNet.Numerics.Interpolation</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.LinearAlgebra/index.htm">MathNet.Numerics.LinearAlgebra</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.LinearAlgebra.Complex/index.htm">MathNet.Numerics.LinearAlgebra.Complex</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.LinearAlgebra.Complex.Solvers/index.htm">MathNet.Numerics.LinearAlgebra.Complex.Solvers</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.LinearAlgebra.Complex32/index.htm">MathNet.Numerics.LinearAlgebra.Complex32</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.LinearAlgebra.Complex32.Solvers/index.htm">MathNet.Numerics.LinearAlgebra.Complex32.Solvers</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.LinearAlgebra.Double/index.htm">MathNet.Numerics.LinearAlgebra.Double</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.LinearAlgebra.Double.Solvers/index.htm">MathNet.Numerics.LinearAlgebra.Double.Solvers</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.LinearAlgebra.Factorization/index.htm">MathNet.Numerics.LinearAlgebra.Factorization</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.LinearAlgebra.Single/index.htm">MathNet.Numerics.LinearAlgebra.Single</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.LinearAlgebra.Single.Solvers/index.htm">MathNet.Numerics.LinearAlgebra.Single.Solvers</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.LinearAlgebra.Solvers/index.htm">MathNet.Numerics.LinearAlgebra.Solvers</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.LinearAlgebra.Storage/index.htm">MathNet.Numerics.LinearAlgebra.Storage</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.LinearRegression/index.htm" class="current">MathNet.Numerics.LinearRegression</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.OdeSolvers/index.htm">MathNet.Numerics.OdeSolvers</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.Optimization/index.htm">MathNet.Numerics.Optimization</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.Optimization.LineSearch/index.htm">MathNet.Numerics.Optimization.LineSearch</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.Optimization.ObjectiveFunctions/index.htm">MathNet.Numerics.Optimization.ObjectiveFunctions</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.Optimization.TrustRegion/index.htm">MathNet.Numerics.Optimization.TrustRegion</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.Providers/index.htm">MathNet.Numerics.Providers</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.Providers.FourierTransform/index.htm">MathNet.Numerics.Providers.FourierTransform</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.Providers.LinearAlgebra/index.htm">MathNet.Numerics.Providers.LinearAlgebra</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.Providers.SparseSolver/index.htm">MathNet.Numerics.Providers.SparseSolver</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.Random/index.htm">MathNet.Numerics.Random</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.RootFinding/index.htm">MathNet.Numerics.RootFinding</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.Statistics/index.htm">MathNet.Numerics.Statistics</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.Statistics.Mcmc/index.htm">MathNet.Numerics.Statistics.Mcmc</a>
|
|
</li>
|
|
</ul>
|
|
</div>
|
|
</div><div id="types">
|
|
<h2 class="fixed">Types in MathNet.Numerics.LinearRegression</h2>
|
|
<div class="scroll">
|
|
<ul>
|
|
<li>
|
|
<a href="../MathNet.Numerics.LinearRegression/DirectRegressionMethod.htm">DirectRegressionMethod</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.LinearRegression/MultipleRegression.htm" class="current">MultipleRegression</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.LinearRegression/SimpleRegression.htm">SimpleRegression</a>
|
|
</li>
|
|
<li>
|
|
<a href="../MathNet.Numerics.LinearRegression/WeightedRegression.htm">WeightedRegression</a>
|
|
</li>
|
|
</ul>
|
|
</div>
|
|
</div>
|
|
<div class="header">
|
|
<p class="class"><strong>Type</strong> MultipleRegression</p>
|
|
<p><strong>Namespace</strong> MathNet.Numerics.LinearRegression</p>
|
|
</div>
|
|
<div class="sub-header">
|
|
|
|
|
|
<h3 class="section">Static Functions</h3>
|
|
<ul>
|
|
<li><a href="../MathNet.Numerics.LinearRegression/MultipleRegression.htm#DirectMethod``1">DirectMethod<T></a></li>
|
|
<li><a href="../MathNet.Numerics.LinearRegression/MultipleRegression.htm#DirectMethod``1">DirectMethod<T></a></li>
|
|
<li><a href="../MathNet.Numerics.LinearRegression/MultipleRegression.htm#DirectMethod``1">DirectMethod<T></a></li>
|
|
<li><a href="../MathNet.Numerics.LinearRegression/MultipleRegression.htm#DirectMethod``1">DirectMethod<T></a></li>
|
|
<li><a href="../MathNet.Numerics.LinearRegression/MultipleRegression.htm#NormalEquations``1">NormalEquations<T></a></li>
|
|
<li><a href="../MathNet.Numerics.LinearRegression/MultipleRegression.htm#NormalEquations``1">NormalEquations<T></a></li>
|
|
<li><a href="../MathNet.Numerics.LinearRegression/MultipleRegression.htm#NormalEquations``1">NormalEquations<T></a></li>
|
|
<li><a href="../MathNet.Numerics.LinearRegression/MultipleRegression.htm#NormalEquations``1">NormalEquations<T></a></li>
|
|
<li><a href="../MathNet.Numerics.LinearRegression/MultipleRegression.htm#QR``1">QR<T></a></li>
|
|
<li><a href="../MathNet.Numerics.LinearRegression/MultipleRegression.htm#QR``1">QR<T></a></li>
|
|
<li><a href="../MathNet.Numerics.LinearRegression/MultipleRegression.htm#QR``1">QR<T></a></li>
|
|
<li><a href="../MathNet.Numerics.LinearRegression/MultipleRegression.htm#QR``1">QR<T></a></li>
|
|
<li><a href="../MathNet.Numerics.LinearRegression/MultipleRegression.htm#Svd``1">Svd<T></a></li>
|
|
<li><a href="../MathNet.Numerics.LinearRegression/MultipleRegression.htm#Svd``1">Svd<T></a></li>
|
|
<li><a href="../MathNet.Numerics.LinearRegression/MultipleRegression.htm#Svd``1">Svd<T></a></li>
|
|
<li><a href="../MathNet.Numerics.LinearRegression/MultipleRegression.htm#Svd``1">Svd<T></a></li>
|
|
</ul>
|
|
|
|
|
|
|
|
</div>
|
|
|
|
|
|
|
|
<h3 class="section">Public Static Functions</h3>
|
|
|
|
<div id="DirectMethod``1" class="method">
|
|
<h4><a href="../MathNet.Numerics.LinearAlgebra/Vector`1.htm">Vector<T></a> <strong>DirectMethod<T></strong>(<a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a> x, <a href="../MathNet.Numerics.LinearAlgebra/Vector`1.htm">Vector<T></a> y, <a href="../MathNet.Numerics.LinearRegression/DirectRegressionMethod.htm">DirectRegressionMethod</a> method)</h4>
|
|
<div class="content">Find the model parameters β such that X*β with predictor X becomes as close to response Y as possible, with least squares residuals.
|
|
|
|
|
|
<div class="parameters">
|
|
<h5>Parameters</h5>
|
|
|
|
<h6><code><a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a></code> x</h6>
|
|
<p class="comments">Predictor matrix X </p>
|
|
<h6><code><a href="../MathNet.Numerics.LinearAlgebra/Vector`1.htm">Vector<T></a></code> y</h6>
|
|
<p class="comments">Response vector Y </p>
|
|
<h6><code><a href="../MathNet.Numerics.LinearRegression/DirectRegressionMethod.htm">DirectRegressionMethod</a></code> method</h6>
|
|
<p class="comments">The direct method to be used to compute the regression. </p>
|
|
</div>
|
|
|
|
<div class="return">
|
|
<h5>Return</h5>
|
|
<h6><code><a href="../MathNet.Numerics.LinearAlgebra/Vector`1.htm">Vector<T></a></code></h6>
|
|
<p>Best fitting vector for model parameters β </p>
|
|
</div>
|
|
|
|
</div>
|
|
</div>
|
|
<div id="DirectMethod``1" class="method">
|
|
<h4><a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a> <strong>DirectMethod<T></strong>(<a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a> x, <a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a> y, <a href="../MathNet.Numerics.LinearRegression/DirectRegressionMethod.htm">DirectRegressionMethod</a> method)</h4>
|
|
<div class="content">Find the model parameters β such that X*β with predictor X becomes as close to response Y as possible, with least squares residuals.
|
|
|
|
|
|
<div class="parameters">
|
|
<h5>Parameters</h5>
|
|
|
|
<h6><code><a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a></code> x</h6>
|
|
<p class="comments">Predictor matrix X </p>
|
|
<h6><code><a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a></code> y</h6>
|
|
<p class="comments">Response matrix Y </p>
|
|
<h6><code><a href="../MathNet.Numerics.LinearRegression/DirectRegressionMethod.htm">DirectRegressionMethod</a></code> method</h6>
|
|
<p class="comments">The direct method to be used to compute the regression. </p>
|
|
</div>
|
|
|
|
<div class="return">
|
|
<h5>Return</h5>
|
|
<h6><code><a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a></code></h6>
|
|
<p>Best fitting vector for model parameters β </p>
|
|
</div>
|
|
|
|
</div>
|
|
</div>
|
|
<div id="DirectMethod``1" class="method">
|
|
<h4><span title="MathNet.Numerics.LinearRegression.T[]">T[]</span> <strong>DirectMethod<T></strong>(<span title="MathNet.Numerics.LinearRegression.T[][]">T[][]</span> x, <span title="MathNet.Numerics.LinearRegression.T[]">T[]</span> y, <span title="System.bool">bool</span> intercept, <a href="../MathNet.Numerics.LinearRegression/DirectRegressionMethod.htm">DirectRegressionMethod</a> method)</h4>
|
|
<div class="content">
|
|
|
|
|
|
|
|
|
|
</div>
|
|
</div>
|
|
<div id="DirectMethod``1" class="method">
|
|
<h4><span title="MathNet.Numerics.LinearRegression.T[]">T[]</span> <strong>DirectMethod<T></strong>(<span title="System.Collections.Generic.IEnumerable<Tuple<T[], T>>">IEnumerable<Tuple<T[], T>></span> samples, <span title="System.bool">bool</span> intercept, <a href="../MathNet.Numerics.LinearRegression/DirectRegressionMethod.htm">DirectRegressionMethod</a> method)</h4>
|
|
<div class="content">Find the model parameters β such that their linear combination with all predictor-arrays in X become as close to their response in Y as possible, with least squares residuals.
|
|
Uses the cholesky decomposition of the normal equations.
|
|
|
|
|
|
<div class="parameters">
|
|
<h5>Parameters</h5>
|
|
|
|
<h6><code><span title="System.Collections.Generic.IEnumerable<Tuple<T[], T>>">IEnumerable<Tuple<T[], T>></span></code> samples</h6>
|
|
<p class="comments">Sequence of predictor-arrays and their response. </p>
|
|
<h6><code><span title="System.bool">bool</span></code> intercept</h6>
|
|
<p class="comments">True if an intercept should be added as first artificial predictor value. Default = false. </p>
|
|
<h6><code><a href="../MathNet.Numerics.LinearRegression/DirectRegressionMethod.htm">DirectRegressionMethod</a></code> method</h6>
|
|
<p class="comments">The direct method to be used to compute the regression. </p>
|
|
</div>
|
|
|
|
<div class="return">
|
|
<h5>Return</h5>
|
|
<h6><code><span title="MathNet.Numerics.LinearRegression.T[]">T[]</span></code></h6>
|
|
<p>Best fitting list of model parameters β for each element in the predictor-arrays. </p>
|
|
</div>
|
|
|
|
</div>
|
|
</div>
|
|
<div id="NormalEquations``1" class="method">
|
|
<h4><a href="../MathNet.Numerics.LinearAlgebra/Vector`1.htm">Vector<T></a> <strong>NormalEquations<T></strong>(<a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a> x, <a href="../MathNet.Numerics.LinearAlgebra/Vector`1.htm">Vector<T></a> y)</h4>
|
|
<div class="content">Find the model parameters β such that X*β with predictor X becomes as close to response Y as possible, with least squares residuals.
|
|
Uses the cholesky decomposition of the normal equations.
|
|
|
|
|
|
<div class="parameters">
|
|
<h5>Parameters</h5>
|
|
|
|
<h6><code><a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a></code> x</h6>
|
|
<p class="comments">Predictor matrix X </p>
|
|
<h6><code><a href="../MathNet.Numerics.LinearAlgebra/Vector`1.htm">Vector<T></a></code> y</h6>
|
|
<p class="comments">Response vector Y </p>
|
|
</div>
|
|
|
|
<div class="return">
|
|
<h5>Return</h5>
|
|
<h6><code><a href="../MathNet.Numerics.LinearAlgebra/Vector`1.htm">Vector<T></a></code></h6>
|
|
<p>Best fitting vector for model parameters β </p>
|
|
</div>
|
|
|
|
</div>
|
|
</div>
|
|
<div id="NormalEquations``1" class="method">
|
|
<h4><a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a> <strong>NormalEquations<T></strong>(<a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a> x, <a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a> y)</h4>
|
|
<div class="content">Find the model parameters β such that X*β with predictor X becomes as close to response Y as possible, with least squares residuals.
|
|
Uses the cholesky decomposition of the normal equations.
|
|
|
|
|
|
<div class="parameters">
|
|
<h5>Parameters</h5>
|
|
|
|
<h6><code><a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a></code> x</h6>
|
|
<p class="comments">Predictor matrix X </p>
|
|
<h6><code><a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a></code> y</h6>
|
|
<p class="comments">Response matrix Y </p>
|
|
</div>
|
|
|
|
<div class="return">
|
|
<h5>Return</h5>
|
|
<h6><code><a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a></code></h6>
|
|
<p>Best fitting vector for model parameters β </p>
|
|
</div>
|
|
|
|
</div>
|
|
</div>
|
|
<div id="NormalEquations``1" class="method">
|
|
<h4><span title="MathNet.Numerics.LinearRegression.T[]">T[]</span> <strong>NormalEquations<T></strong>(<span title="MathNet.Numerics.LinearRegression.T[][]">T[][]</span> x, <span title="MathNet.Numerics.LinearRegression.T[]">T[]</span> y, <span title="System.bool">bool</span> intercept)</h4>
|
|
<div class="content">
|
|
|
|
|
|
|
|
|
|
</div>
|
|
</div>
|
|
<div id="NormalEquations``1" class="method">
|
|
<h4><span title="MathNet.Numerics.LinearRegression.T[]">T[]</span> <strong>NormalEquations<T></strong>(<span title="System.Collections.Generic.IEnumerable<Tuple<T[], T>>">IEnumerable<Tuple<T[], T>></span> samples, <span title="System.bool">bool</span> intercept)</h4>
|
|
<div class="content">Find the model parameters β such that their linear combination with all predictor-arrays in X become as close to their response in Y as possible, with least squares residuals.
|
|
Uses the cholesky decomposition of the normal equations.
|
|
|
|
|
|
<div class="parameters">
|
|
<h5>Parameters</h5>
|
|
|
|
<h6><code><span title="System.Collections.Generic.IEnumerable<Tuple<T[], T>>">IEnumerable<Tuple<T[], T>></span></code> samples</h6>
|
|
<p class="comments">Sequence of predictor-arrays and their response. </p>
|
|
<h6><code><span title="System.bool">bool</span></code> intercept</h6>
|
|
<p class="comments">True if an intercept should be added as first artificial predictor value. Default = false. </p>
|
|
</div>
|
|
|
|
<div class="return">
|
|
<h5>Return</h5>
|
|
<h6><code><span title="MathNet.Numerics.LinearRegression.T[]">T[]</span></code></h6>
|
|
<p>Best fitting list of model parameters β for each element in the predictor-arrays. </p>
|
|
</div>
|
|
|
|
</div>
|
|
</div>
|
|
<div id="QR``1" class="method">
|
|
<h4><a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a> <strong>QR<T></strong>(<a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a> x, <a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a> y)</h4>
|
|
<div class="content">Find the model parameters β such that X*β with predictor X becomes as close to response Y as possible, with least squares residuals.
|
|
Uses an orthogonal decomposition and is therefore more numerically stable than the normal equations but also slower.
|
|
|
|
|
|
<div class="parameters">
|
|
<h5>Parameters</h5>
|
|
|
|
<h6><code><a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a></code> x</h6>
|
|
<p class="comments">Predictor matrix X </p>
|
|
<h6><code><a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a></code> y</h6>
|
|
<p class="comments">Response matrix Y </p>
|
|
</div>
|
|
|
|
<div class="return">
|
|
<h5>Return</h5>
|
|
<h6><code><a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a></code></h6>
|
|
<p>Best fitting vector for model parameters β </p>
|
|
</div>
|
|
|
|
</div>
|
|
</div>
|
|
<div id="QR``1" class="method">
|
|
<h4><span title="MathNet.Numerics.LinearRegression.T[]">T[]</span> <strong>QR<T></strong>(<span title="MathNet.Numerics.LinearRegression.T[][]">T[][]</span> x, <span title="MathNet.Numerics.LinearRegression.T[]">T[]</span> y, <span title="System.bool">bool</span> intercept)</h4>
|
|
<div class="content">
|
|
|
|
|
|
|
|
|
|
</div>
|
|
</div>
|
|
<div id="QR``1" class="method">
|
|
<h4><a href="../MathNet.Numerics.LinearAlgebra/Vector`1.htm">Vector<T></a> <strong>QR<T></strong>(<a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a> x, <a href="../MathNet.Numerics.LinearAlgebra/Vector`1.htm">Vector<T></a> y)</h4>
|
|
<div class="content">Find the model parameters β such that X*β with predictor X becomes as close to response Y as possible, with least squares residuals.
|
|
Uses an orthogonal decomposition and is therefore more numerically stable than the normal equations but also slower.
|
|
|
|
|
|
<div class="parameters">
|
|
<h5>Parameters</h5>
|
|
|
|
<h6><code><a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a></code> x</h6>
|
|
<p class="comments">Predictor matrix X </p>
|
|
<h6><code><a href="../MathNet.Numerics.LinearAlgebra/Vector`1.htm">Vector<T></a></code> y</h6>
|
|
<p class="comments">Response vector Y </p>
|
|
</div>
|
|
|
|
<div class="return">
|
|
<h5>Return</h5>
|
|
<h6><code><a href="../MathNet.Numerics.LinearAlgebra/Vector`1.htm">Vector<T></a></code></h6>
|
|
<p>Best fitting vector for model parameters β </p>
|
|
</div>
|
|
|
|
</div>
|
|
</div>
|
|
<div id="QR``1" class="method">
|
|
<h4><span title="MathNet.Numerics.LinearRegression.T[]">T[]</span> <strong>QR<T></strong>(<span title="System.Collections.Generic.IEnumerable<Tuple<T[], T>>">IEnumerable<Tuple<T[], T>></span> samples, <span title="System.bool">bool</span> intercept)</h4>
|
|
<div class="content">Find the model parameters β such that their linear combination with all predictor-arrays in X become as close to their response in Y as possible, with least squares residuals.
|
|
Uses an orthogonal decomposition and is therefore more numerically stable than the normal equations but also slower.
|
|
|
|
|
|
<div class="parameters">
|
|
<h5>Parameters</h5>
|
|
|
|
<h6><code><span title="System.Collections.Generic.IEnumerable<Tuple<T[], T>>">IEnumerable<Tuple<T[], T>></span></code> samples</h6>
|
|
<p class="comments">Sequence of predictor-arrays and their response. </p>
|
|
<h6><code><span title="System.bool">bool</span></code> intercept</h6>
|
|
<p class="comments">True if an intercept should be added as first artificial predictor value. Default = false. </p>
|
|
</div>
|
|
|
|
<div class="return">
|
|
<h5>Return</h5>
|
|
<h6><code><span title="MathNet.Numerics.LinearRegression.T[]">T[]</span></code></h6>
|
|
<p>Best fitting list of model parameters β for each element in the predictor-arrays. </p>
|
|
</div>
|
|
|
|
</div>
|
|
</div>
|
|
<div id="Svd``1" class="method">
|
|
<h4><a href="../MathNet.Numerics.LinearAlgebra/Vector`1.htm">Vector<T></a> <strong>Svd<T></strong>(<a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a> x, <a href="../MathNet.Numerics.LinearAlgebra/Vector`1.htm">Vector<T></a> y)</h4>
|
|
<div class="content">Find the model parameters β such that X*β with predictor X becomes as close to response Y as possible, with least squares residuals.
|
|
Uses a singular value decomposition and is therefore more numerically stable (especially if ill-conditioned) than the normal equations or QR but also slower.
|
|
|
|
|
|
<div class="parameters">
|
|
<h5>Parameters</h5>
|
|
|
|
<h6><code><a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a></code> x</h6>
|
|
<p class="comments">Predictor matrix X </p>
|
|
<h6><code><a href="../MathNet.Numerics.LinearAlgebra/Vector`1.htm">Vector<T></a></code> y</h6>
|
|
<p class="comments">Response vector Y </p>
|
|
</div>
|
|
|
|
<div class="return">
|
|
<h5>Return</h5>
|
|
<h6><code><a href="../MathNet.Numerics.LinearAlgebra/Vector`1.htm">Vector<T></a></code></h6>
|
|
<p>Best fitting vector for model parameters β </p>
|
|
</div>
|
|
|
|
</div>
|
|
</div>
|
|
<div id="Svd``1" class="method">
|
|
<h4><a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a> <strong>Svd<T></strong>(<a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a> x, <a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a> y)</h4>
|
|
<div class="content">Find the model parameters β such that X*β with predictor X becomes as close to response Y as possible, with least squares residuals.
|
|
Uses a singular value decomposition and is therefore more numerically stable (especially if ill-conditioned) than the normal equations or QR but also slower.
|
|
|
|
|
|
<div class="parameters">
|
|
<h5>Parameters</h5>
|
|
|
|
<h6><code><a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a></code> x</h6>
|
|
<p class="comments">Predictor matrix X </p>
|
|
<h6><code><a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a></code> y</h6>
|
|
<p class="comments">Response matrix Y </p>
|
|
</div>
|
|
|
|
<div class="return">
|
|
<h5>Return</h5>
|
|
<h6><code><a href="../MathNet.Numerics.LinearAlgebra/Matrix`1.htm">Matrix<T></a></code></h6>
|
|
<p>Best fitting vector for model parameters β </p>
|
|
</div>
|
|
|
|
</div>
|
|
</div>
|
|
<div id="Svd``1" class="method">
|
|
<h4><span title="MathNet.Numerics.LinearRegression.T[]">T[]</span> <strong>Svd<T></strong>(<span title="MathNet.Numerics.LinearRegression.T[][]">T[][]</span> x, <span title="MathNet.Numerics.LinearRegression.T[]">T[]</span> y, <span title="System.bool">bool</span> intercept)</h4>
|
|
<div class="content">
|
|
|
|
|
|
|
|
|
|
</div>
|
|
</div>
|
|
<div id="Svd``1" class="method">
|
|
<h4><span title="MathNet.Numerics.LinearRegression.T[]">T[]</span> <strong>Svd<T></strong>(<span title="System.Collections.Generic.IEnumerable<Tuple<T[], T>>">IEnumerable<Tuple<T[], T>></span> samples, <span title="System.bool">bool</span> intercept)</h4>
|
|
<div class="content">Find the model parameters β such that their linear combination with all predictor-arrays in X become as close to their response in Y as possible, with least squares residuals.
|
|
Uses a singular value decomposition and is therefore more numerically stable (especially if ill-conditioned) than the normal equations or QR but also slower.
|
|
|
|
|
|
<div class="parameters">
|
|
<h5>Parameters</h5>
|
|
|
|
<h6><code><span title="System.Collections.Generic.IEnumerable<Tuple<T[], T>>">IEnumerable<Tuple<T[], T>></span></code> samples</h6>
|
|
<p class="comments">Sequence of predictor-arrays and their response. </p>
|
|
<h6><code><span title="System.bool">bool</span></code> intercept</h6>
|
|
<p class="comments">True if an intercept should be added as first artificial predictor value. Default = false. </p>
|
|
</div>
|
|
|
|
<div class="return">
|
|
<h5>Return</h5>
|
|
<h6><code><span title="MathNet.Numerics.LinearRegression.T[]">T[]</span></code></h6>
|
|
<p>Best fitting list of model parameters β for each element in the predictor-arrays. </p>
|
|
</div>
|
|
|
|
</div>
|
|
</div>
|
|
|
|
|
|
<div id="footer">
|
|
<p>Based on v5.0.0.0 of MathNet.Numerics (Math.NET Numerics)</p>
|
|
<p>Generated by <a href="http://docu.jagregory.com">docu</a></p>
|
|
</div>
|
|
</body>
|
|
</html>
|