Mercurial > hg > de.mpg.mpiwg.itgroup.digilib.plugin
view libs/commons-math-2.1/docs/apidocs/src-html/org/apache/commons/math/stat/inference/OneWayAnovaImpl.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.inference;<a name="line.17"></a> <FONT color="green">018</FONT> <a name="line.18"></a> <FONT color="green">019</FONT> import java.util.Collection;<a name="line.19"></a> <FONT color="green">020</FONT> <a name="line.20"></a> <FONT color="green">021</FONT> import org.apache.commons.math.MathException;<a name="line.21"></a> <FONT color="green">022</FONT> import org.apache.commons.math.MathRuntimeException;<a name="line.22"></a> <FONT color="green">023</FONT> import org.apache.commons.math.distribution.FDistribution;<a name="line.23"></a> <FONT color="green">024</FONT> import org.apache.commons.math.distribution.FDistributionImpl;<a name="line.24"></a> <FONT color="green">025</FONT> import org.apache.commons.math.stat.descriptive.summary.Sum;<a name="line.25"></a> <FONT color="green">026</FONT> import org.apache.commons.math.stat.descriptive.summary.SumOfSquares;<a name="line.26"></a> <FONT color="green">027</FONT> <a name="line.27"></a> <FONT color="green">028</FONT> <a name="line.28"></a> <FONT color="green">029</FONT> /**<a name="line.29"></a> <FONT color="green">030</FONT> * Implements one-way ANOVA statistics defined in the {@link OneWayAnovaImpl}<a name="line.30"></a> <FONT color="green">031</FONT> * interface.<a name="line.31"></a> <FONT color="green">032</FONT> *<a name="line.32"></a> <FONT color="green">033</FONT> * <p>Uses the<a name="line.33"></a> <FONT color="green">034</FONT> * {@link org.apache.commons.math.distribution.FDistribution<a name="line.34"></a> <FONT color="green">035</FONT> * commons-math F Distribution implementation} to estimate exact p-values.</p><a name="line.35"></a> <FONT color="green">036</FONT> *<a name="line.36"></a> <FONT color="green">037</FONT> * <p>This implementation is based on a description at<a name="line.37"></a> <FONT color="green">038</FONT> * http://faculty.vassar.edu/lowry/ch13pt1.html</p><a name="line.38"></a> <FONT color="green">039</FONT> * <pre><a name="line.39"></a> <FONT color="green">040</FONT> * Abbreviations: bg = between groups,<a name="line.40"></a> <FONT color="green">041</FONT> * wg = within groups,<a name="line.41"></a> <FONT color="green">042</FONT> * ss = sum squared deviations<a name="line.42"></a> <FONT color="green">043</FONT> * </pre><a name="line.43"></a> <FONT color="green">044</FONT> *<a name="line.44"></a> <FONT color="green">045</FONT> * @since 1.2<a name="line.45"></a> <FONT color="green">046</FONT> * @version $Revision: 825917 $ $Date: 2009-10-16 10:47:27 -0400 (Fri, 16 Oct 2009) $<a name="line.46"></a> <FONT color="green">047</FONT> */<a name="line.47"></a> <FONT color="green">048</FONT> public class OneWayAnovaImpl implements OneWayAnova {<a name="line.48"></a> <FONT color="green">049</FONT> <a name="line.49"></a> <FONT color="green">050</FONT> /**<a name="line.50"></a> <FONT color="green">051</FONT> * Default constructor.<a name="line.51"></a> <FONT color="green">052</FONT> */<a name="line.52"></a> <FONT color="green">053</FONT> public OneWayAnovaImpl() {<a name="line.53"></a> <FONT color="green">054</FONT> }<a name="line.54"></a> <FONT color="green">055</FONT> <a name="line.55"></a> <FONT color="green">056</FONT> /**<a name="line.56"></a> <FONT color="green">057</FONT> * {@inheritDoc}<p><a name="line.57"></a> <FONT color="green">058</FONT> * This implementation computes the F statistic using the definitional<a name="line.58"></a> <FONT color="green">059</FONT> * formula<pre><a name="line.59"></a> <FONT color="green">060</FONT> * F = msbg/mswg</pre><a name="line.60"></a> <FONT color="green">061</FONT> * where<pre><a name="line.61"></a> <FONT color="green">062</FONT> * msbg = between group mean square<a name="line.62"></a> <FONT color="green">063</FONT> * mswg = within group mean square</pre><a name="line.63"></a> <FONT color="green">064</FONT> * are as defined <a href="http://faculty.vassar.edu/lowry/ch13pt1.html"><a name="line.64"></a> <FONT color="green">065</FONT> * here</a></p><a name="line.65"></a> <FONT color="green">066</FONT> */<a name="line.66"></a> <FONT color="green">067</FONT> public double anovaFValue(Collection<double[]> categoryData)<a name="line.67"></a> <FONT color="green">068</FONT> throws IllegalArgumentException, MathException {<a name="line.68"></a> <FONT color="green">069</FONT> AnovaStats a = anovaStats(categoryData);<a name="line.69"></a> <FONT color="green">070</FONT> return a.F;<a name="line.70"></a> <FONT color="green">071</FONT> }<a name="line.71"></a> <FONT color="green">072</FONT> <a name="line.72"></a> <FONT color="green">073</FONT> /**<a name="line.73"></a> <FONT color="green">074</FONT> * {@inheritDoc}<p><a name="line.74"></a> <FONT color="green">075</FONT> * This implementation uses the<a name="line.75"></a> <FONT color="green">076</FONT> * {@link org.apache.commons.math.distribution.FDistribution<a name="line.76"></a> <FONT color="green">077</FONT> * commons-math F Distribution implementation} to estimate the exact<a name="line.77"></a> <FONT color="green">078</FONT> * p-value, using the formula<pre><a name="line.78"></a> <FONT color="green">079</FONT> * p = 1 - cumulativeProbability(F)</pre><a name="line.79"></a> <FONT color="green">080</FONT> * where <code>F</code> is the F value and <code>cumulativeProbability</code><a name="line.80"></a> <FONT color="green">081</FONT> * is the commons-math implementation of the F distribution.</p><a name="line.81"></a> <FONT color="green">082</FONT> */<a name="line.82"></a> <FONT color="green">083</FONT> public double anovaPValue(Collection<double[]> categoryData)<a name="line.83"></a> <FONT color="green">084</FONT> throws IllegalArgumentException, MathException {<a name="line.84"></a> <FONT color="green">085</FONT> AnovaStats a = anovaStats(categoryData);<a name="line.85"></a> <FONT color="green">086</FONT> FDistribution fdist = new FDistributionImpl(a.dfbg, a.dfwg);<a name="line.86"></a> <FONT color="green">087</FONT> return 1.0 - fdist.cumulativeProbability(a.F);<a name="line.87"></a> <FONT color="green">088</FONT> }<a name="line.88"></a> <FONT color="green">089</FONT> <a name="line.89"></a> <FONT color="green">090</FONT> /**<a name="line.90"></a> <FONT color="green">091</FONT> * {@inheritDoc}<p><a name="line.91"></a> <FONT color="green">092</FONT> * This implementation uses the<a name="line.92"></a> <FONT color="green">093</FONT> * {@link org.apache.commons.math.distribution.FDistribution<a name="line.93"></a> <FONT color="green">094</FONT> * commons-math F Distribution implementation} to estimate the exact<a name="line.94"></a> <FONT color="green">095</FONT> * p-value, using the formula<pre><a name="line.95"></a> <FONT color="green">096</FONT> * p = 1 - cumulativeProbability(F)</pre><a name="line.96"></a> <FONT color="green">097</FONT> * where <code>F</code> is the F value and <code>cumulativeProbability</code><a name="line.97"></a> <FONT color="green">098</FONT> * is the commons-math implementation of the F distribution.</p><a name="line.98"></a> <FONT color="green">099</FONT> * <p>True is returned iff the estimated p-value is less than alpha.</p><a name="line.99"></a> <FONT color="green">100</FONT> */<a name="line.100"></a> <FONT color="green">101</FONT> public boolean anovaTest(Collection<double[]> categoryData, double alpha)<a name="line.101"></a> <FONT color="green">102</FONT> throws IllegalArgumentException, MathException {<a name="line.102"></a> <FONT color="green">103</FONT> if ((alpha <= 0) || (alpha > 0.5)) {<a name="line.103"></a> <FONT color="green">104</FONT> throw MathRuntimeException.createIllegalArgumentException(<a name="line.104"></a> <FONT color="green">105</FONT> "out of bounds significance level {0}, must be between {1} and {2}",<a name="line.105"></a> <FONT color="green">106</FONT> alpha, 0, 0.5);<a name="line.106"></a> <FONT color="green">107</FONT> }<a name="line.107"></a> <FONT color="green">108</FONT> return anovaPValue(categoryData) < alpha;<a name="line.108"></a> <FONT color="green">109</FONT> }<a name="line.109"></a> <FONT color="green">110</FONT> <a name="line.110"></a> <FONT color="green">111</FONT> <a name="line.111"></a> <FONT color="green">112</FONT> /**<a name="line.112"></a> <FONT color="green">113</FONT> * This method actually does the calculations (except P-value).<a name="line.113"></a> <FONT color="green">114</FONT> *<a name="line.114"></a> <FONT color="green">115</FONT> * @param categoryData <code>Collection</code> of <code>double[]</code><a name="line.115"></a> <FONT color="green">116</FONT> * arrays each containing data for one category<a name="line.116"></a> <FONT color="green">117</FONT> * @return computed AnovaStats<a name="line.117"></a> <FONT color="green">118</FONT> * @throws IllegalArgumentException if categoryData does not meet<a name="line.118"></a> <FONT color="green">119</FONT> * preconditions specified in the interface definition<a name="line.119"></a> <FONT color="green">120</FONT> * @throws MathException if an error occurs computing the Anova stats<a name="line.120"></a> <FONT color="green">121</FONT> */<a name="line.121"></a> <FONT color="green">122</FONT> private AnovaStats anovaStats(Collection<double[]> categoryData)<a name="line.122"></a> <FONT color="green">123</FONT> throws IllegalArgumentException, MathException {<a name="line.123"></a> <FONT color="green">124</FONT> <a name="line.124"></a> <FONT color="green">125</FONT> // check if we have enough categories<a name="line.125"></a> <FONT color="green">126</FONT> if (categoryData.size() < 2) {<a name="line.126"></a> <FONT color="green">127</FONT> throw MathRuntimeException.createIllegalArgumentException(<a name="line.127"></a> <FONT color="green">128</FONT> "two or more categories required, got {0}",<a name="line.128"></a> <FONT color="green">129</FONT> categoryData.size());<a name="line.129"></a> <FONT color="green">130</FONT> }<a name="line.130"></a> <FONT color="green">131</FONT> <a name="line.131"></a> <FONT color="green">132</FONT> // check if each category has enough data and all is double[]<a name="line.132"></a> <FONT color="green">133</FONT> for (double[] array : categoryData) {<a name="line.133"></a> <FONT color="green">134</FONT> if (array.length <= 1) {<a name="line.134"></a> <FONT color="green">135</FONT> throw MathRuntimeException.createIllegalArgumentException(<a name="line.135"></a> <FONT color="green">136</FONT> "two or more values required in each category, one has {0}",<a name="line.136"></a> <FONT color="green">137</FONT> array.length);<a name="line.137"></a> <FONT color="green">138</FONT> }<a name="line.138"></a> <FONT color="green">139</FONT> }<a name="line.139"></a> <FONT color="green">140</FONT> <a name="line.140"></a> <FONT color="green">141</FONT> int dfwg = 0;<a name="line.141"></a> <FONT color="green">142</FONT> double sswg = 0;<a name="line.142"></a> <FONT color="green">143</FONT> Sum totsum = new Sum();<a name="line.143"></a> <FONT color="green">144</FONT> SumOfSquares totsumsq = new SumOfSquares();<a name="line.144"></a> <FONT color="green">145</FONT> int totnum = 0;<a name="line.145"></a> <FONT color="green">146</FONT> <a name="line.146"></a> <FONT color="green">147</FONT> for (double[] data : categoryData) {<a name="line.147"></a> <FONT color="green">148</FONT> <a name="line.148"></a> <FONT color="green">149</FONT> Sum sum = new Sum();<a name="line.149"></a> <FONT color="green">150</FONT> SumOfSquares sumsq = new SumOfSquares();<a name="line.150"></a> <FONT color="green">151</FONT> int num = 0;<a name="line.151"></a> <FONT color="green">152</FONT> <a name="line.152"></a> <FONT color="green">153</FONT> for (int i = 0; i < data.length; i++) {<a name="line.153"></a> <FONT color="green">154</FONT> double val = data[i];<a name="line.154"></a> <FONT color="green">155</FONT> <a name="line.155"></a> <FONT color="green">156</FONT> // within category<a name="line.156"></a> <FONT color="green">157</FONT> num++;<a name="line.157"></a> <FONT color="green">158</FONT> sum.increment(val);<a name="line.158"></a> <FONT color="green">159</FONT> sumsq.increment(val);<a name="line.159"></a> <FONT color="green">160</FONT> <a name="line.160"></a> <FONT color="green">161</FONT> // for all categories<a name="line.161"></a> <FONT color="green">162</FONT> totnum++;<a name="line.162"></a> <FONT color="green">163</FONT> totsum.increment(val);<a name="line.163"></a> <FONT color="green">164</FONT> totsumsq.increment(val);<a name="line.164"></a> <FONT color="green">165</FONT> }<a name="line.165"></a> <FONT color="green">166</FONT> dfwg += num - 1;<a name="line.166"></a> <FONT color="green">167</FONT> double ss = sumsq.getResult() - sum.getResult() * sum.getResult() / num;<a name="line.167"></a> <FONT color="green">168</FONT> sswg += ss;<a name="line.168"></a> <FONT color="green">169</FONT> }<a name="line.169"></a> <FONT color="green">170</FONT> double sst = totsumsq.getResult() - totsum.getResult() *<a name="line.170"></a> <FONT color="green">171</FONT> totsum.getResult()/totnum;<a name="line.171"></a> <FONT color="green">172</FONT> double ssbg = sst - sswg;<a name="line.172"></a> <FONT color="green">173</FONT> int dfbg = categoryData.size() - 1;<a name="line.173"></a> <FONT color="green">174</FONT> double msbg = ssbg/dfbg;<a name="line.174"></a> <FONT color="green">175</FONT> double mswg = sswg/dfwg;<a name="line.175"></a> <FONT color="green">176</FONT> double F = msbg/mswg;<a name="line.176"></a> <FONT color="green">177</FONT> <a name="line.177"></a> <FONT color="green">178</FONT> return new AnovaStats(dfbg, dfwg, F);<a name="line.178"></a> <FONT color="green">179</FONT> }<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> Convenience class to pass dfbg,dfwg,F values around within AnovaImpl.<a name="line.182"></a> <FONT color="green">183</FONT> No get/set methods provided.<a name="line.183"></a> <FONT color="green">184</FONT> */<a name="line.184"></a> <FONT color="green">185</FONT> private static class AnovaStats {<a name="line.185"></a> <FONT color="green">186</FONT> <a name="line.186"></a> <FONT color="green">187</FONT> /** Degrees of freedom in numerator (between groups). */<a name="line.187"></a> <FONT color="green">188</FONT> private int dfbg;<a name="line.188"></a> <FONT color="green">189</FONT> <a name="line.189"></a> <FONT color="green">190</FONT> /** Degrees of freedom in denominator (within groups). */<a name="line.190"></a> <FONT color="green">191</FONT> private int dfwg;<a name="line.191"></a> <FONT color="green">192</FONT> <a name="line.192"></a> <FONT color="green">193</FONT> /** Statistic. */<a name="line.193"></a> <FONT color="green">194</FONT> private double F;<a name="line.194"></a> <FONT color="green">195</FONT> <a name="line.195"></a> <FONT color="green">196</FONT> /**<a name="line.196"></a> <FONT color="green">197</FONT> * Constructor<a name="line.197"></a> <FONT color="green">198</FONT> * @param dfbg degrees of freedom in numerator (between groups)<a name="line.198"></a> <FONT color="green">199</FONT> * @param dfwg degrees of freedom in denominator (within groups)<a name="line.199"></a> <FONT color="green">200</FONT> * @param F statistic<a name="line.200"></a> <FONT color="green">201</FONT> */<a name="line.201"></a> <FONT color="green">202</FONT> private AnovaStats(int dfbg, int dfwg, double F) {<a name="line.202"></a> <FONT color="green">203</FONT> this.dfbg = dfbg;<a name="line.203"></a> <FONT color="green">204</FONT> this.dfwg = dfwg;<a name="line.204"></a> <FONT color="green">205</FONT> this.F = F;<a name="line.205"></a> <FONT color="green">206</FONT> }<a name="line.206"></a> <FONT color="green">207</FONT> }<a name="line.207"></a> <FONT color="green">208</FONT> <a name="line.208"></a> <FONT color="green">209</FONT> }<a name="line.209"></a> </PRE> </BODY> </HTML>