javanpst.distributions.tests

Class FisherDistribution

java.lang.Object

javanpst.distributions.tests.FisherDistribution

public class FisherDistribution
extends java.lang.Object

An implementation of the Fisher's test distribution. Uses a Singleton pattern to ensure only an instance of the class is allowed.

Method Summary

Modifier and Type	Method and Description
double	computeAsymptoticProbability(double Q, int freedom) Compute asymptotic p-value, following a chi-square distribution
double	computeLeftExactProbability(int N, int n1, int n2, int Y, int n00) Computes exact left tail of Fisher distribution.
double	computeRightExactProbability(int N, int n1, int n2, int Y, int n00) Computes exact right tail of Fisher distribution.
static FisherDistribution	getInstance() Singleton pattern access to the distribution

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Method Detail

getInstance

public static FisherDistribution getInstance()

Singleton pattern access to the distribution

Returns:

the instance of the distribution

computeLeftExactProbability

public double computeLeftExactProbability(int N,
                                          int n1,
                                          int n2,
                                          int Y,
                                          int n00)

Computes exact left tail of Fisher distribution.

Parameters:

N - number of samples

n1 - sum of the samples of the first row

n2 - sum of the samples of the second row

Y - sum of the samples of the first column

n00 - samples in first column, first row

Returns:

p-value computed

computeRightExactProbability

public double computeRightExactProbability(int N,
                                           int n1,
                                           int n2,
                                           int Y,
                                           int n00)

Computes exact right tail of Fisher distribution.

Parameters:

N - number of samples

n1 - sum of the samples of the first row

n2 - sum of the samples of the second row

Y - sum of the samples of the first column

n00 - samples in first column, first row

Returns:

p-value computed

computeAsymptoticProbability

public double computeAsymptoticProbability(double Q,
                                           int freedom)

Compute asymptotic p-value, following a chi-square distribution

Parameters:

Q - Fisher statistic

freedom - degrees of freedom

Returns:

p-value computed