Apache Commons Math 3.6.1 · org.apache.commons.math3.stat.inference.MannWhitneyUTest

Modifier and Type	Field and Description
private NaturalRanking	naturalRanking Ranking algorithm.

Access	Constructor and Description
public	MannWhitneyUTest() Create a test instance using where NaN's are left in place and ties get the average of applicable ranks.
public	MannWhitneyUTest(final NaNStrategy specifies the strategy that should be used for Double.NaN's nanStrategy, final TiesStrategy specifies the strategy that should be used for ties tiesStrategy) Create a test instance using the given strategies for NaN's and ties.

Method Summary

Modifier and Type	Method and Description
private double	Returns: two-sided asymptotic p-value calculateAsymptoticPValue(final double smallest Mann-Whitney U value Umin, final int number of subjects in first sample n1, final int number of subjects in second sample n2)
private double[]	Returns: concatenated array concatenateSamples(final double[] first sample x, final double[] second sample y) Concatenate the samples into one array.
private void	ensureDataConformance(final double[] first sample x, final double[] second sample y) Ensures that the provided arrays fulfills the assumptions.
public double	Returns: Mann-Whitney U statistic (maximum of U^x and U^y) mannWhitneyU(final double[] the first sample x, final double[] the second sample y) Computes the Mann-Whitney U statistic comparing mean for two independent samples possibly of different length.
public double	Returns: asymptotic p-value mannWhitneyUTest(final double[] the first sample x, final double[] the second sample y) Returns the asymptotic observed significance level, or p-value, associated with a Mann-Whitney U statistic comparing mean for two independent samples.

Inherited from java.lang.Object:: clone equals finalize getClass hashCode notify notifyAll toString wait wait wait

naturalRanking	back to summary
private NaturalRanking naturalRanking Ranking algorithm.

MannWhitneyUTest	back to summary
public MannWhitneyUTest() Create a test instance using where NaN's are left in place and ties get the average of applicable ranks. Use this unless you are very sure of what you are doing.

MannWhitneyUTest	back to summary
public MannWhitneyUTest(final NaNStrategy nanStrategy, final TiesStrategy tiesStrategy) Create a test instance using the given strategies for NaN's and ties. Only use this if you are sure of what you are doing. Parameters nanStrategy:NaNStrategy specifies the strategy that should be used for Double.NaN's tiesStrategy:TiesStrategy specifies the strategy that should be used for ties

Method Detail

calculateAsymptoticPValue	back to summary
private double calculateAsymptoticPValue(final double Umin, final int n1, final int n2) throws ConvergenceException, MaxCountExceededException Parameters Umin:double smallest Mann-Whitney U value n1:int number of subjects in first sample n2:int number of subjects in second sample Returns:double two-sided asymptotic p-value Exceptions ConvergenceException: if the p-value can not be computed due to a convergence error MaxCountExceededException: if the maximum number of iterations is exceeded

calculateAsymptoticPValue

back to summary

private double calculateAsymptoticPValue(final double Umin, final int n1, final int n2) throws ConvergenceException, MaxCountExceededException

Parameters

Umin:double: smallest Mann-Whitney U value
n1:int: number of subjects in first sample
n2:int: number of subjects in second sample

Returns:double

two-sided asymptotic p-value

Exceptions

ConvergenceException:: if the p-value can not be computed due to a convergence error
MaxCountExceededException:: if the maximum number of iterations is exceeded

concatenateSamples	back to summary
private double[] concatenateSamples(final double[] x, final double[] y) Concatenate the samples into one array. Parameters x:double[] first sample y:double[] second sample Returns:double[] concatenated array

concatenateSamples

back to summary

private double[] concatenateSamples(final double[] x, final double[] y)

Concatenate the samples into one array.

Parameters

x:double[]: first sample
y:double[]: second sample

Returns:double[]

concatenated array

ensureDataConformance back to summary

ensureDataConformance	back to summary
private void ensureDataConformance(final double[] x, final double[] y) throws NullArgumentException, NoDataException Ensures that the provided arrays fulfills the assumptions. Parameters x:double[] first sample y:double[] second sample Exceptions NullArgumentException: if `x` or `y` are `null`. NoDataException: if `x` or `y` are zero-length.

private void ensureDataConformance(final double[] x, final double[] y) throws NullArgumentException, NoDataException

Ensures that the provided arrays fulfills the assumptions.

Parameters

x:double[]: first sample
y:double[]: second sample

Exceptions

NullArgumentException:: if x or y are null.
NoDataException:: if x or y are zero-length.

mannWhitneyU back to summary

mannWhitneyU	back to summary
public double mannWhitneyU(final double[] x, final double[] y) throws NullArgumentException, NoDataException Computes the Mann-Whitney U statistic comparing mean for two independent samples possibly of different length. This statistic can be used to perform a Mann-Whitney U test evaluating the null hypothesis that the two independent samples has equal mean. Let X_i denote the i'th individual of the first sample and Y_j the j'th individual in the second sample. Note that the samples would often have different length. Preconditions: All observations in the two samples are independent. The observations are at least ordinal (continuous are also ordinal). Parameters x:double[] the first sample y:double[] the second sample Returns:double Mann-Whitney U statistic (maximum of U^x and U^y) Exceptions NullArgumentException: if `x` or `y` are `null`. NoDataException: if `x` or `y` are zero-length.

public double mannWhitneyU(final double[] x, final double[] y) throws NullArgumentException, NoDataException

Computes the Mann-Whitney U statistic comparing mean for two independent samples possibly of different length.

This statistic can be used to perform a Mann-Whitney U test evaluating the null hypothesis that the two independent samples has equal mean.

Let X_i denote the i'th individual of the first sample and Y_j the j'th individual in the second sample. Note that the samples would often have different length.

Preconditions:

All observations in the two samples are independent.
The observations are at least ordinal (continuous are also ordinal).

Parameters

x:double[]: the first sample
y:double[]: the second sample

Returns:double

Mann-Whitney U statistic (maximum of U^x and U^y)

Exceptions

NullArgumentException:: if x or y are null.
NoDataException:: if x or y are zero-length.

mannWhitneyUTest back to summary

mannWhitneyUTest	back to summary
public double mannWhitneyUTest(final double[] x, final double[] y) throws NullArgumentException, NoDataException, ConvergenceException, MaxCountExceededException Returns the asymptotic observed significance level, or p-value, associated with a Mann-Whitney U statistic comparing mean for two independent samples. Let X_i denote the i'th individual of the first sample and Y_j the j'th individual in the second sample. Note that the samples would often have different length. Preconditions: All observations in the two samples are independent. The observations are at least ordinal (continuous are also ordinal). Ties give rise to biased variance at the moment. See e.g. http://mlsc.lboro.ac.uk/resources/statistics/Mannwhitney.pdf. Parameters x:double[] the first sample y:double[] the second sample Returns:double asymptotic p-value Exceptions NullArgumentException: if `x` or `y` are `null`. NoDataException: if `x` or `y` are zero-length. ConvergenceException: if the p-value can not be computed due to a convergence error MaxCountExceededException: if the maximum number of iterations is exceeded

public double mannWhitneyUTest(final double[] x, final double[] y) throws NullArgumentException, NoDataException, ConvergenceException, MaxCountExceededException

Returns the asymptotic observed significance level, or p-value, associated with a Mann-Whitney U statistic comparing mean for two independent samples.

Let X_i denote the i'th individual of the first sample and Y_j the j'th individual in the second sample. Note that the samples would often have different length.

Preconditions:

All observations in the two samples are independent.
The observations are at least ordinal (continuous are also ordinal).

Ties give rise to biased variance at the moment. See e.g. http://mlsc.lboro.ac.uk/resources/statistics/Mannwhitney.pdf.

Parameters

x:double[]: the first sample
y:double[]: the second sample

Returns:double

asymptotic p-value

Exceptions

NullArgumentException:: if x or y are null.
NoDataException:: if x or y are zero-length.
ConvergenceException:: if the p-value can not be computed due to a convergence error
MaxCountExceededException:: if the maximum number of iterations is exceeded

public Class MannWhitneyUTest

Field Summary

Constructor Summary

Method Summary

Field Detail

Constructor Detail

Method Detail