Mercurial > hg > de.mpg.mpiwg.itgroup.digilib.plugin
view libs/commons-math-2.1/docs/apidocs/src-html/org/apache/commons/math/stat/regression/AbstractMultipleLinearRegression.html @ 13:cbf34dd4d7e6
commons-math-2.1 added
| author | dwinter |
|---|---|
| date | Tue, 04 Jan 2011 10:02:07 +0100 |
| parents | |
| children |
line wrap: on
line source
<HTML> <BODY BGCOLOR="white"> <PRE> <FONT color="green">001</FONT> /*<a name="line.1"></a> <FONT color="green">002</FONT> * Licensed to the Apache Software Foundation (ASF) under one or more<a name="line.2"></a> <FONT color="green">003</FONT> * contributor license agreements. See the NOTICE file distributed with<a name="line.3"></a> <FONT color="green">004</FONT> * this work for additional information regarding copyright ownership.<a name="line.4"></a> <FONT color="green">005</FONT> * The ASF licenses this file to You under the Apache License, Version 2.0<a name="line.5"></a> <FONT color="green">006</FONT> * (the "License"); you may not use this file except in compliance with<a name="line.6"></a> <FONT color="green">007</FONT> * the License. You may obtain a copy of the License at<a name="line.7"></a> <FONT color="green">008</FONT> *<a name="line.8"></a> <FONT color="green">009</FONT> * http://www.apache.org/licenses/LICENSE-2.0<a name="line.9"></a> <FONT color="green">010</FONT> *<a name="line.10"></a> <FONT color="green">011</FONT> * Unless required by applicable law or agreed to in writing, software<a name="line.11"></a> <FONT color="green">012</FONT> * distributed under the License is distributed on an "AS IS" BASIS,<a name="line.12"></a> <FONT color="green">013</FONT> * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.<a name="line.13"></a> <FONT color="green">014</FONT> * See the License for the specific language governing permissions and<a name="line.14"></a> <FONT color="green">015</FONT> * limitations under the License.<a name="line.15"></a> <FONT color="green">016</FONT> */<a name="line.16"></a> <FONT color="green">017</FONT> package org.apache.commons.math.stat.regression;<a name="line.17"></a> <FONT color="green">018</FONT> <a name="line.18"></a> <FONT color="green">019</FONT> import org.apache.commons.math.MathRuntimeException;<a name="line.19"></a> <FONT color="green">020</FONT> import org.apache.commons.math.linear.RealMatrix;<a name="line.20"></a> <FONT color="green">021</FONT> import org.apache.commons.math.linear.Array2DRowRealMatrix;<a name="line.21"></a> <FONT color="green">022</FONT> import org.apache.commons.math.linear.RealVector;<a name="line.22"></a> <FONT color="green">023</FONT> import org.apache.commons.math.linear.ArrayRealVector;<a name="line.23"></a> <FONT color="green">024</FONT> <a name="line.24"></a> <FONT color="green">025</FONT> /**<a name="line.25"></a> <FONT color="green">026</FONT> * Abstract base class for implementations of MultipleLinearRegression.<a name="line.26"></a> <FONT color="green">027</FONT> * @version $Revision: 811685 $ $Date: 2009-09-05 13:36:48 -0400 (Sat, 05 Sep 2009) $<a name="line.27"></a> <FONT color="green">028</FONT> * @since 2.0<a name="line.28"></a> <FONT color="green">029</FONT> */<a name="line.29"></a> <FONT color="green">030</FONT> public abstract class AbstractMultipleLinearRegression implements<a name="line.30"></a> <FONT color="green">031</FONT> MultipleLinearRegression {<a name="line.31"></a> <FONT color="green">032</FONT> <a name="line.32"></a> <FONT color="green">033</FONT> /** X sample data. */<a name="line.33"></a> <FONT color="green">034</FONT> protected RealMatrix X;<a name="line.34"></a> <FONT color="green">035</FONT> <a name="line.35"></a> <FONT color="green">036</FONT> /** Y sample data. */<a name="line.36"></a> <FONT color="green">037</FONT> protected RealVector Y;<a name="line.37"></a> <FONT color="green">038</FONT> <a name="line.38"></a> <FONT color="green">039</FONT> /**<a name="line.39"></a> <FONT color="green">040</FONT> * Loads model x and y sample data from a flat array of data, overriding any previous sample.<a name="line.40"></a> <FONT color="green">041</FONT> * Assumes that rows are concatenated with y values first in each row.<a name="line.41"></a> <FONT color="green">042</FONT> *<a name="line.42"></a> <FONT color="green">043</FONT> * @param data input data array<a name="line.43"></a> <FONT color="green">044</FONT> * @param nobs number of observations (rows)<a name="line.44"></a> <FONT color="green">045</FONT> * @param nvars number of independent variables (columns, not counting y)<a name="line.45"></a> <FONT color="green">046</FONT> */<a name="line.46"></a> <FONT color="green">047</FONT> public void newSampleData(double[] data, int nobs, int nvars) {<a name="line.47"></a> <FONT color="green">048</FONT> double[] y = new double[nobs];<a name="line.48"></a> <FONT color="green">049</FONT> double[][] x = new double[nobs][nvars + 1];<a name="line.49"></a> <FONT color="green">050</FONT> int pointer = 0;<a name="line.50"></a> <FONT color="green">051</FONT> for (int i = 0; i < nobs; i++) {<a name="line.51"></a> <FONT color="green">052</FONT> y[i] = data[pointer++];<a name="line.52"></a> <FONT color="green">053</FONT> x[i][0] = 1.0d;<a name="line.53"></a> <FONT color="green">054</FONT> for (int j = 1; j < nvars + 1; j++) {<a name="line.54"></a> <FONT color="green">055</FONT> x[i][j] = data[pointer++];<a name="line.55"></a> <FONT color="green">056</FONT> }<a name="line.56"></a> <FONT color="green">057</FONT> }<a name="line.57"></a> <FONT color="green">058</FONT> this.X = new Array2DRowRealMatrix(x);<a name="line.58"></a> <FONT color="green">059</FONT> this.Y = new ArrayRealVector(y);<a name="line.59"></a> <FONT color="green">060</FONT> }<a name="line.60"></a> <FONT color="green">061</FONT> <a name="line.61"></a> <FONT color="green">062</FONT> /**<a name="line.62"></a> <FONT color="green">063</FONT> * Loads new y sample data, overriding any previous sample<a name="line.63"></a> <FONT color="green">064</FONT> *<a name="line.64"></a> <FONT color="green">065</FONT> * @param y the [n,1] array representing the y sample<a name="line.65"></a> <FONT color="green">066</FONT> */<a name="line.66"></a> <FONT color="green">067</FONT> protected void newYSampleData(double[] y) {<a name="line.67"></a> <FONT color="green">068</FONT> this.Y = new ArrayRealVector(y);<a name="line.68"></a> <FONT color="green">069</FONT> }<a name="line.69"></a> <FONT color="green">070</FONT> <a name="line.70"></a> <FONT color="green">071</FONT> /**<a name="line.71"></a> <FONT color="green">072</FONT> * Loads new x sample data, overriding any previous sample<a name="line.72"></a> <FONT color="green">073</FONT> *<a name="line.73"></a> <FONT color="green">074</FONT> * @param x the [n,k] array representing the x sample<a name="line.74"></a> <FONT color="green">075</FONT> */<a name="line.75"></a> <FONT color="green">076</FONT> protected void newXSampleData(double[][] x) {<a name="line.76"></a> <FONT color="green">077</FONT> this.X = new Array2DRowRealMatrix(x);<a name="line.77"></a> <FONT color="green">078</FONT> }<a name="line.78"></a> <FONT color="green">079</FONT> <a name="line.79"></a> <FONT color="green">080</FONT> /**<a name="line.80"></a> <FONT color="green">081</FONT> * Validates sample data.<a name="line.81"></a> <FONT color="green">082</FONT> *<a name="line.82"></a> <FONT color="green">083</FONT> * @param x the [n,k] array representing the x sample<a name="line.83"></a> <FONT color="green">084</FONT> * @param y the [n,1] array representing the y sample<a name="line.84"></a> <FONT color="green">085</FONT> * @throws IllegalArgumentException if the x and y array data are not<a name="line.85"></a> <FONT color="green">086</FONT> * compatible for the regression<a name="line.86"></a> <FONT color="green">087</FONT> */<a name="line.87"></a> <FONT color="green">088</FONT> protected void validateSampleData(double[][] x, double[] y) {<a name="line.88"></a> <FONT color="green">089</FONT> if ((x == null) || (y == null) || (x.length != y.length)) {<a name="line.89"></a> <FONT color="green">090</FONT> throw MathRuntimeException.createIllegalArgumentException(<a name="line.90"></a> <FONT color="green">091</FONT> "dimension mismatch {0} != {1}",<a name="line.91"></a> <FONT color="green">092</FONT> (x == null) ? 0 : x.length,<a name="line.92"></a> <FONT color="green">093</FONT> (y == null) ? 0 : y.length);<a name="line.93"></a> <FONT color="green">094</FONT> } else if ((x.length > 0) && (x[0].length > x.length)) {<a name="line.94"></a> <FONT color="green">095</FONT> throw MathRuntimeException.createIllegalArgumentException(<a name="line.95"></a> <FONT color="green">096</FONT> "not enough data ({0} rows) for this many predictors ({1} predictors)",<a name="line.96"></a> <FONT color="green">097</FONT> x.length, x[0].length);<a name="line.97"></a> <FONT color="green">098</FONT> }<a name="line.98"></a> <FONT color="green">099</FONT> }<a name="line.99"></a> <FONT color="green">100</FONT> <a name="line.100"></a> <FONT color="green">101</FONT> /**<a name="line.101"></a> <FONT color="green">102</FONT> * Validates sample data.<a name="line.102"></a> <FONT color="green">103</FONT> *<a name="line.103"></a> <FONT color="green">104</FONT> * @param x the [n,k] array representing the x sample<a name="line.104"></a> <FONT color="green">105</FONT> * @param covariance the [n,n] array representing the covariance matrix<a name="line.105"></a> <FONT color="green">106</FONT> * @throws IllegalArgumentException if the x sample data or covariance<a name="line.106"></a> <FONT color="green">107</FONT> * matrix are not compatible for the regression<a name="line.107"></a> <FONT color="green">108</FONT> */<a name="line.108"></a> <FONT color="green">109</FONT> protected void validateCovarianceData(double[][] x, double[][] covariance) {<a name="line.109"></a> <FONT color="green">110</FONT> if (x.length != covariance.length) {<a name="line.110"></a> <FONT color="green">111</FONT> throw MathRuntimeException.createIllegalArgumentException(<a name="line.111"></a> <FONT color="green">112</FONT> "dimension mismatch {0} != {1}", x.length, covariance.length);<a name="line.112"></a> <FONT color="green">113</FONT> }<a name="line.113"></a> <FONT color="green">114</FONT> if (covariance.length > 0 && covariance.length != covariance[0].length) {<a name="line.114"></a> <FONT color="green">115</FONT> throw MathRuntimeException.createIllegalArgumentException(<a name="line.115"></a> <FONT color="green">116</FONT> "a {0}x{1} matrix was provided instead of a square matrix",<a name="line.116"></a> <FONT color="green">117</FONT> covariance.length, covariance[0].length);<a name="line.117"></a> <FONT color="green">118</FONT> }<a name="line.118"></a> <FONT color="green">119</FONT> }<a name="line.119"></a> <FONT color="green">120</FONT> <a name="line.120"></a> <FONT color="green">121</FONT> /**<a name="line.121"></a> <FONT color="green">122</FONT> * {@inheritDoc}<a name="line.122"></a> <FONT color="green">123</FONT> */<a name="line.123"></a> <FONT color="green">124</FONT> public double[] estimateRegressionParameters() {<a name="line.124"></a> <FONT color="green">125</FONT> RealVector b = calculateBeta();<a name="line.125"></a> <FONT color="green">126</FONT> return b.getData();<a name="line.126"></a> <FONT color="green">127</FONT> }<a name="line.127"></a> <FONT color="green">128</FONT> <a name="line.128"></a> <FONT color="green">129</FONT> /**<a name="line.129"></a> <FONT color="green">130</FONT> * {@inheritDoc}<a name="line.130"></a> <FONT color="green">131</FONT> */<a name="line.131"></a> <FONT color="green">132</FONT> public double[] estimateResiduals() {<a name="line.132"></a> <FONT color="green">133</FONT> RealVector b = calculateBeta();<a name="line.133"></a> <FONT color="green">134</FONT> RealVector e = Y.subtract(X.operate(b));<a name="line.134"></a> <FONT color="green">135</FONT> return e.getData();<a name="line.135"></a> <FONT color="green">136</FONT> }<a name="line.136"></a> <FONT color="green">137</FONT> <a name="line.137"></a> <FONT color="green">138</FONT> /**<a name="line.138"></a> <FONT color="green">139</FONT> * {@inheritDoc}<a name="line.139"></a> <FONT color="green">140</FONT> */<a name="line.140"></a> <FONT color="green">141</FONT> public double[][] estimateRegressionParametersVariance() {<a name="line.141"></a> <FONT color="green">142</FONT> return calculateBetaVariance().getData();<a name="line.142"></a> <FONT color="green">143</FONT> }<a name="line.143"></a> <FONT color="green">144</FONT> <a name="line.144"></a> <FONT color="green">145</FONT> /**<a name="line.145"></a> <FONT color="green">146</FONT> * {@inheritDoc}<a name="line.146"></a> <FONT color="green">147</FONT> */<a name="line.147"></a> <FONT color="green">148</FONT> public double[] estimateRegressionParametersStandardErrors() {<a name="line.148"></a> <FONT color="green">149</FONT> double[][] betaVariance = estimateRegressionParametersVariance();<a name="line.149"></a> <FONT color="green">150</FONT> double sigma = calculateYVariance();<a name="line.150"></a> <FONT color="green">151</FONT> int length = betaVariance[0].length;<a name="line.151"></a> <FONT color="green">152</FONT> double[] result = new double[length];<a name="line.152"></a> <FONT color="green">153</FONT> for (int i = 0; i < length; i++) {<a name="line.153"></a> <FONT color="green">154</FONT> result[i] = Math.sqrt(sigma * betaVariance[i][i]);<a name="line.154"></a> <FONT color="green">155</FONT> }<a name="line.155"></a> <FONT color="green">156</FONT> return result;<a name="line.156"></a> <FONT color="green">157</FONT> }<a name="line.157"></a> <FONT color="green">158</FONT> <a name="line.158"></a> <FONT color="green">159</FONT> /**<a name="line.159"></a> <FONT color="green">160</FONT> * {@inheritDoc}<a name="line.160"></a> <FONT color="green">161</FONT> */<a name="line.161"></a> <FONT color="green">162</FONT> public double estimateRegressandVariance() {<a name="line.162"></a> <FONT color="green">163</FONT> return calculateYVariance();<a name="line.163"></a> <FONT color="green">164</FONT> }<a name="line.164"></a> <FONT color="green">165</FONT> <a name="line.165"></a> <FONT color="green">166</FONT> /**<a name="line.166"></a> <FONT color="green">167</FONT> * Calculates the beta of multiple linear regression in matrix notation.<a name="line.167"></a> <FONT color="green">168</FONT> *<a name="line.168"></a> <FONT color="green">169</FONT> * @return beta<a name="line.169"></a> <FONT color="green">170</FONT> */<a name="line.170"></a> <FONT color="green">171</FONT> protected abstract RealVector calculateBeta();<a name="line.171"></a> <FONT color="green">172</FONT> <a name="line.172"></a> <FONT color="green">173</FONT> /**<a name="line.173"></a> <FONT color="green">174</FONT> * Calculates the beta variance of multiple linear regression in matrix<a name="line.174"></a> <FONT color="green">175</FONT> * notation.<a name="line.175"></a> <FONT color="green">176</FONT> *<a name="line.176"></a> <FONT color="green">177</FONT> * @return beta variance<a name="line.177"></a> <FONT color="green">178</FONT> */<a name="line.178"></a> <FONT color="green">179</FONT> protected abstract RealMatrix calculateBetaVariance();<a name="line.179"></a> <FONT color="green">180</FONT> <a name="line.180"></a> <FONT color="green">181</FONT> /**<a name="line.181"></a> <FONT color="green">182</FONT> * Calculates the Y variance of multiple linear regression.<a name="line.182"></a> <FONT color="green">183</FONT> *<a name="line.183"></a> <FONT color="green">184</FONT> * @return Y variance<a name="line.184"></a> <FONT color="green">185</FONT> */<a name="line.185"></a> <FONT color="green">186</FONT> protected abstract double calculateYVariance();<a name="line.186"></a> <FONT color="green">187</FONT> <a name="line.187"></a> <FONT color="green">188</FONT> /**<a name="line.188"></a> <FONT color="green">189</FONT> * Calculates the residuals of multiple linear regression in matrix<a name="line.189"></a> <FONT color="green">190</FONT> * notation.<a name="line.190"></a> <FONT color="green">191</FONT> *<a name="line.191"></a> <FONT color="green">192</FONT> * <pre><a name="line.192"></a> <FONT color="green">193</FONT> * u = y - X * b<a name="line.193"></a> <FONT color="green">194</FONT> * </pre><a name="line.194"></a> <FONT color="green">195</FONT> *<a name="line.195"></a> <FONT color="green">196</FONT> * @return The residuals [n,1] matrix<a name="line.196"></a> <FONT color="green">197</FONT> */<a name="line.197"></a> <FONT color="green">198</FONT> protected RealVector calculateResiduals() {<a name="line.198"></a> <FONT color="green">199</FONT> RealVector b = calculateBeta();<a name="line.199"></a> <FONT color="green">200</FONT> return Y.subtract(X.operate(b));<a name="line.200"></a> <FONT color="green">201</FONT> }<a name="line.201"></a> <FONT color="green">202</FONT> <a name="line.202"></a> <FONT color="green">203</FONT> }<a name="line.203"></a> </PRE> </BODY> </HTML>