home | career | drupal | java | mac | mysql | perl | scala | uml | unix  

Java example source code file (GTest.java)

This example Java source code file (GTest.java) is included in the alvinalexander.com "Java Source Code Warehouse" project. The intent of this project is to help you "Learn Java by Example" TM.

Learn more about this Java project at its project page.

Java - Java tags/keywords

chisquareddistribution, dimensionmismatchexception, gtest, maxcountexceededexception, notpositiveexception, notstrictlypositiveexception, outofrangeexception, zeroexception

The GTest.java Java example source code

 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *      http://www.apache.org/licenses/LICENSE-2.0
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * See the License for the specific language governing permissions and
 * limitations under the License.
package org.apache.commons.math3.stat.inference;

import org.apache.commons.math3.distribution.ChiSquaredDistribution;
import org.apache.commons.math3.exception.DimensionMismatchException;
import org.apache.commons.math3.exception.MaxCountExceededException;
import org.apache.commons.math3.exception.NotPositiveException;
import org.apache.commons.math3.exception.NotStrictlyPositiveException;
import org.apache.commons.math3.exception.OutOfRangeException;
import org.apache.commons.math3.exception.ZeroException;
import org.apache.commons.math3.exception.util.LocalizedFormats;
import org.apache.commons.math3.util.FastMath;
import org.apache.commons.math3.util.MathArrays;

 * Implements <a href="http://en.wikipedia.org/wiki/G-test">G Test
 * statistics.
 * <p>This is known in statistical genetics as the McDonald-Kreitman test.
 * The implementation handles both known and unknown distributions.</p>
 * <p>Two samples tests can be used when the distribution is unknown a priori
 * but provided by one sample, or when the hypothesis under test is that the two
 * samples come from the same underlying distribution.</p>
 * @since 3.1
public class GTest {

     * Computes the <a href="http://en.wikipedia.org/wiki/G-test">G statistic
     * for Goodness of Fit</a> comparing {@code observed} and {@code expected}
     * frequency counts.
     * <p>This statistic can be used to perform a G test (Log-Likelihood Ratio
     * Test) evaluating the null hypothesis that the observed counts follow the
     * expected distribution.</p>
     * <p>Preconditions: 
    * <li>Expected counts must all be positive. * <li>Observed counts must all be ≥ 0. * <li>The observed and expected arrays must have the same length and their * common length must be at least 2. </li>

* * <p>If any of the preconditions are not met, a * {@code MathIllegalArgumentException} is thrown.</p> * * <p>Note:This implementation rescales the * {@code expected} array if necessary to ensure that the sum of the * expected and observed counts are equal.</p> * * @param observed array of observed frequency counts * @param expected array of expected frequency counts * @return G-Test statistic * @throws NotPositiveException if {@code observed} has negative entries * @throws NotStrictlyPositiveException if {@code expected} has entries that * are not strictly positive * @throws DimensionMismatchException if the array lengths do not match or * are less than 2. */ public double g(final double[] expected, final long[] observed) throws NotPositiveException, NotStrictlyPositiveException, DimensionMismatchException { if (expected.length < 2) { throw new DimensionMismatchException(expected.length, 2); } if (expected.length != observed.length) { throw new DimensionMismatchException(expected.length, observed.length); } MathArrays.checkPositive(expected); MathArrays.checkNonNegative(observed); double sumExpected = 0d; double sumObserved = 0d; for (int i = 0; i < observed.length; i++) { sumExpected += expected[i]; sumObserved += observed[i]; } double ratio = 1d; boolean rescale = false; if (FastMath.abs(sumExpected - sumObserved) > 10E-6) { ratio = sumObserved / sumExpected; rescale = true; } double sum = 0d; for (int i = 0; i < observed.length; i++) { final double dev = rescale ? FastMath.log((double) observed[i] / (ratio * expected[i])) : FastMath.log((double) observed[i] / expected[i]); sum += ((double) observed[i]) * dev; } return 2d * sum; } /** * Returns the <i>observed significance level, or , * associated with a G-Test for goodness of fit</a> comparing the * {@code observed} frequency counts to those in the {@code expected} array. * * <p>The number returned is the smallest significance level at which one * can reject the null hypothesis that the observed counts conform to the * frequency distribution described by the expected counts.</p> * * <p>The probability returned is the tail probability beyond * {@link #g(double[], long[]) g(expected, observed)} * in the ChiSquare distribution with degrees of freedom one less than the * common length of {@code expected} and {@code observed}.</p> * * <p> Preconditions:

my book on functional programming


new blog posts


Copyright 1998-2019 Alvin Alexander, alvinalexander.com
All Rights Reserved.

A percentage of advertising revenue from
pages under the /java/jwarehouse URI on this website is
paid back to open source projects.