dev.nm.stat.test.distribution.pearson

Class FisherExactDistribution

java.lang.Object

dev.nm.stat.distribution.univariate.EmpiricalDistribution

dev.nm.stat.test.distribution.pearson.FisherExactDistribution

All Implemented Interfaces:

ProbabilityDistribution

public class FisherExactDistribution
extends EmpiricalDistribution

Fisher's exact test distribution is, as its name states, exact, and can therefore be used regardless of the sample characteristics. It converges asymptotically to Chi-square distribution for a large and well balanced sample. For a set of small, sparse, or unbalanced data, the exact and asymptotic p-values can be quite different and may lead to opposite conclusions concerning the hypothesis of interest. The exact distribution becomes difficult to calculate with large samples or well-balanced tables, but fortunately these are precisely the conditions where the chi-square distribution is appropriate.

See Also:

Wikipedia: Fisher's exact test

Constructor Summary

Constructors

Constructor and Description
FisherExactDistribution(int[] rowSums, int[] colSums, int nSims) Construct the distribution for Fisher's exact test.
FisherExactDistribution(int[] rowSums, int[] colSums, int nSims, RandomLongGenerator uniform) Construct the distribution for Fisher's exact test.

Method Summary

Methods inherited from class dev.nm.stat.distribution.univariate.EmpiricalDistribution

cdf, density, entropy, kurtosis, mean, median, moment, nSamples, quantile, skew, toArray, variance

Methods inherited from class java.lang.Object

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

Constructor Detail

FisherExactDistribution

public FisherExactDistribution(int[] rowSums,
                               int[] colSums,
                               int nSims,
                               RandomLongGenerator uniform)

Construct the distribution for Fisher's exact test.

Parameters:

rowSums - the row totals

colSums - the column totals

nSims - the number of simulations

uniform - a uniform random number generator

FisherExactDistribution

public FisherExactDistribution(int[] rowSums,
                               int[] colSums,
                               int nSims)

Construct the distribution for Fisher's exact test.

Parameters:

rowSums - the row totals

colSums - the column totals

nSims - the number of simulations