org.apache.commons.math.distribution.HypergeometricDistributionImpl Maven / Gradle / Ivy
Go to download
Show more of this group Show more artifacts with this name
Show all versions of commons-math Show documentation
Show all versions of commons-math Show documentation
The Math project is a library of lightweight, self-contained mathematics and statistics components addressing the most common practical problems not immediately available in the Java programming language or commons-lang.
/*
* 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,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.commons.math.distribution;
import java.io.Serializable;
import org.apache.commons.math.MathRuntimeException;
import org.apache.commons.math.util.MathUtils;
/**
* The default implementation of {@link HypergeometricDistribution}.
*
* @version $Revision: 772119 $ $Date: 2009-05-06 05:43:28 -0400 (Wed, 06 May 2009) $
*/
public class HypergeometricDistributionImpl extends AbstractIntegerDistribution
implements HypergeometricDistribution, Serializable
{
/** Serializable version identifier */
private static final long serialVersionUID = -436928820673516179L;
/** The number of successes in the population. */
private int numberOfSuccesses;
/** The population size. */
private int populationSize;
/** The sample size. */
private int sampleSize;
/**
* Construct a new hypergeometric distribution with the given the population
* size, the number of successes in the population, and the sample size.
* @param populationSize the population size.
* @param numberOfSuccesses number of successes in the population.
* @param sampleSize the sample size.
*/
public HypergeometricDistributionImpl(int populationSize,
int numberOfSuccesses, int sampleSize) {
super();
if (numberOfSuccesses > populationSize) {
throw MathRuntimeException.createIllegalArgumentException(
"number of successes ({0}) must be less than or equal to population size ({1})",
numberOfSuccesses, populationSize);
}
if (sampleSize > populationSize) {
throw MathRuntimeException.createIllegalArgumentException(
"sample size ({0}) must be less than or equal to population size ({1})",
sampleSize, populationSize);
}
setPopulationSize(populationSize);
setSampleSize(sampleSize);
setNumberOfSuccesses(numberOfSuccesses);
}
/**
* For this distribution, X, this method returns P(X ≤ x).
* @param x the value at which the PDF is evaluated.
* @return PDF for this distribution.
*/
@Override
public double cumulativeProbability(int x) {
double ret;
int n = getPopulationSize();
int m = getNumberOfSuccesses();
int k = getSampleSize();
int[] domain = getDomain(n, m, k);
if (x < domain[0]) {
ret = 0.0;
} else if(x >= domain[1]) {
ret = 1.0;
} else {
ret = innerCumulativeProbability(domain[0], x, 1, n, m, k);
}
return ret;
}
/**
* Return the domain for the given hypergeometric distribution parameters.
* @param n the population size.
* @param m number of successes in the population.
* @param k the sample size.
* @return a two element array containing the lower and upper bounds of the
* hypergeometric distribution.
*/
private int[] getDomain(int n, int m, int k){
return new int[]{
getLowerDomain(n, m, k),
getUpperDomain(m, k)
};
}
/**
* Access the domain value lower bound, based on p, used to
* bracket a PDF root.
*
* @param p the desired probability for the critical value
* @return domain value lower bound, i.e.
* P(X < lower bound) < p
*/
@Override
protected int getDomainLowerBound(double p) {
return getLowerDomain(getPopulationSize(), getNumberOfSuccesses(),
getSampleSize());
}
/**
* Access the domain value upper bound, based on p, used to
* bracket a PDF root.
*
* @param p the desired probability for the critical value
* @return domain value upper bound, i.e.
* P(X < upper bound) > p
*/
@Override
protected int getDomainUpperBound(double p) {
return getUpperDomain(getSampleSize(), getNumberOfSuccesses());
}
/**
* Return the lowest domain value for the given hypergeometric distribution
* parameters.
* @param n the population size.
* @param m number of successes in the population.
* @param k the sample size.
* @return the lowest domain value of the hypergeometric distribution.
*/
private int getLowerDomain(int n, int m, int k) {
return Math.max(0, m - (n - k));
}
/**
* Access the number of successes.
* @return the number of successes.
*/
public int getNumberOfSuccesses() {
return numberOfSuccesses;
}
/**
* Access the population size.
* @return the population size.
*/
public int getPopulationSize() {
return populationSize;
}
/**
* Access the sample size.
* @return the sample size.
*/
public int getSampleSize() {
return sampleSize;
}
/**
* Return the highest domain value for the given hypergeometric distribution
* parameters.
* @param m number of successes in the population.
* @param k the sample size.
* @return the highest domain value of the hypergeometric distribution.
*/
private int getUpperDomain(int m, int k){
return Math.min(k, m);
}
/**
* For this distribution, X, this method returns P(X = x).
*
* @param x the value at which the PMF is evaluated.
* @return PMF for this distribution.
*/
public double probability(int x) {
double ret;
int n = getPopulationSize();
int m = getNumberOfSuccesses();
int k = getSampleSize();
int[] domain = getDomain(n, m, k);
if(x < domain[0] || x > domain[1]){
ret = 0.0;
} else {
ret = probability(n, m, k, x);
}
return ret;
}
/**
* For the distribution, X, defined by the given hypergeometric distribution
* parameters, this method returns P(X = x).
*
* @param n the population size.
* @param m number of successes in the population.
* @param k the sample size.
* @param x the value at which the PMF is evaluated.
* @return PMF for the distribution.
*/
private double probability(int n, int m, int k, int x) {
return Math.exp(MathUtils.binomialCoefficientLog(m, x) +
MathUtils.binomialCoefficientLog(n - m, k - x) -
MathUtils.binomialCoefficientLog(n, k));
}
/**
* Modify the number of successes.
* @param num the new number of successes.
* @throws IllegalArgumentException if num is negative.
*/
public void setNumberOfSuccesses(int num) {
if(num < 0){
throw MathRuntimeException.createIllegalArgumentException(
"number of successes must be non-negative ({0})",
num);
}
numberOfSuccesses = num;
}
/**
* Modify the population size.
* @param size the new population size.
* @throws IllegalArgumentException if size is not positive.
*/
public void setPopulationSize(int size) {
if(size <= 0){
throw MathRuntimeException.createIllegalArgumentException(
"population size must be positive ({0})",
size);
}
populationSize = size;
}
/**
* Modify the sample size.
* @param size the new sample size.
* @throws IllegalArgumentException if size is negative.
*/
public void setSampleSize(int size) {
if (size < 0) {
throw MathRuntimeException.createIllegalArgumentException(
"sample size must be positive ({0})",
size);
}
sampleSize = size;
}
/**
* For this distribution, X, this method returns P(X ≥ x).
* @param x the value at which the CDF is evaluated.
* @return upper tail CDF for this distribution.
* @since 1.1
*/
public double upperCumulativeProbability(int x) {
double ret;
int n = getPopulationSize();
int m = getNumberOfSuccesses();
int k = getSampleSize();
int[] domain = getDomain(n, m, k);
if (x < domain[0]) {
ret = 1.0;
} else if(x > domain[1]) {
ret = 0.0;
} else {
ret = innerCumulativeProbability(domain[1], x, -1, n, m, k);
}
return ret;
}
/**
* For this distribution, X, this method returns P(x0 ≤ X ≤ x1). This
* probability is computed by summing the point probabilities for the values
* x0, x0 + 1, x0 + 2, ..., x1, in the order directed by dx.
* @param x0 the inclusive, lower bound
* @param x1 the inclusive, upper bound
* @param dx the direction of summation. 1 indicates summing from x0 to x1.
* 0 indicates summing from x1 to x0.
* @param n the population size.
* @param m number of successes in the population.
* @param k the sample size.
* @return P(x0 ≤ X ≤ x1).
*/
private double innerCumulativeProbability(
int x0, int x1, int dx, int n, int m, int k)
{
double ret = probability(n, m, k, x0);
while (x0 != x1) {
x0 += dx;
ret += probability(n, m, k, x0);
}
return ret;
}
}
© 2015 - 2024 Weber Informatics LLC | Privacy Policy