Java Code Examples for org.apache.commons.math3.distribution.FDistribution#cumulativeProbability()

The following examples show how to use org.apache.commons.math3.distribution.FDistribution#cumulativeProbability() . You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.

Example 1

Source File: TTestSignificanceTestOperator.java From rapidminer-studio with GNU Affero General Public License v3.0

6 votes

private double getProbability(PerformanceCriterion pc1, PerformanceCriterion pc2) {
	double totalDeviation = ((pc1.getAverageCount() - 1) * pc1.getVariance() + (pc2.getAverageCount() - 1)
			* pc2.getVariance())
			/ (pc1.getAverageCount() + pc2.getAverageCount() - 2);
	double factor = 1.0d / (1.0d / pc1.getAverageCount() + 1.0d / pc2.getAverageCount());
	double diff = pc1.getAverage() - pc2.getAverage();
	double t = factor * diff * diff / totalDeviation;
	int secondDegreeOfFreedom = pc1.getAverageCount() + pc2.getAverageCount() - 2;
	double prob;
	// make sure the F-distribution is well defined
	if (secondDegreeOfFreedom > 0) {
		FDistribution fDist = new FDistribution(1, secondDegreeOfFreedom);
		prob = 1 - fDist.cumulativeProbability(t);
	} else {
		// in this case the probability cannot calculated correctly and a 1 is returned, as
		// this result is not significant
		prob = 1;
	}

	return prob;
}

Example 2

Source File: TTestLinearRegressionMethod.java From rapidminer-studio with GNU Affero General Public License v3.0

5 votes

/**
 * Returns the PValue of the attributeIndex-th attribute that expresses the probability that the
 * coefficient is only random.
 *
 * @throws ProcessStoppedException
 */
protected double getPValue(double coefficient, int attributeIndex, LinearRegression regression, boolean useBias,
		double ridge, ExampleSet exampleSet, boolean[] isUsedAttribute, double[] standardDeviations,
		double labelStandardDeviation, FDistribution fdistribution, double generalCorrelation)
		throws UndefinedParameterError, ProcessStoppedException {
	double tolerance = regression.getTolerance(exampleSet, isUsedAttribute, attributeIndex, ridge, useBias);
	double standardError = Math.sqrt((1.0d - generalCorrelation)
			/ (tolerance * (exampleSet.size() - exampleSet.getAttributes().size() - 1.0d)))
			* labelStandardDeviation / standardDeviations[attributeIndex];

	// calculating other statistics
	double tStatistics = coefficient / standardError;
	double probability = fdistribution.cumulativeProbability(tStatistics * tStatistics);
	return probability;
}

Example 3

Source File: AnovaCalculator.java From rapidminer-studio with GNU Affero General Public License v3.0

5 votes

public AnovaSignificanceTestResult(double sumSquaresBetween, double sumSquaresResiduals, int df1, int df2,
		double alpha) {
	this.sumSquaresBetween = sumSquaresBetween;
	this.sumSquaresResiduals = sumSquaresResiduals;
	this.df1 = df1;
	this.df2 = df2;
	this.alpha = alpha;
	this.meanSquaresBetween = sumSquaresBetween / df1;
	this.meanSquaresResiduals = sumSquaresResiduals / df2;
	this.fValue = meanSquaresBetween / meanSquaresResiduals;
	FDistribution fDist = new FDistribution(df1, df2);
	this.prob = 1.0d - fDist.cumulativeProbability(this.fValue);
}

Example 4

Source File: SignificanceTask.java From mzmine2 with GNU General Public License v2.0

4 votes

@Nullable
private Double oneWayAnova(@Nonnull double[][] intensityGroups) {

  int numGroups = intensityGroups.length;
  long numIntensities = Arrays.stream(intensityGroups)
      .flatMapToDouble(Arrays::stream)
      .count();

  double[] groupMeans = Arrays.stream(intensityGroups)
      .mapToDouble(intensities -> Arrays.stream(intensities).average().orElse(0.0))
      .toArray();

  double overallMean = Arrays.stream(intensityGroups)
      .flatMapToDouble(Arrays::stream)
      .average()
      .orElse(0.0);

  double sumOfSquaresOfError = IntStream.range(0, intensityGroups.length)
      .mapToDouble(i -> Arrays
          .stream(intensityGroups[i])
          .map(x -> x - groupMeans[i])
          .map(x -> x * x)
          .sum())
      .sum();

  double sumOfSquaresOfTreatment = (numGroups - 1) * Arrays.stream(groupMeans)
      .map(x -> x - overallMean)
      .map(x -> x * x)
      .sum();

  long degreesOfFreedomOfTreatment = numGroups - 1;
  long degreesOfFreedomOfError = numIntensities - numGroups;

  if (degreesOfFreedomOfTreatment <= 0 || degreesOfFreedomOfError <= 0) {
    return null;
  }

  double meanSquareOfTreatment = sumOfSquaresOfTreatment / degreesOfFreedomOfTreatment;
  double meanSquareOfError = sumOfSquaresOfError / degreesOfFreedomOfError;

  if (meanSquareOfError == 0.0) {
    return null;
  }

  double anovaStatistics = meanSquareOfTreatment / meanSquareOfError;

  Double pValue = null;
  try {
    FDistribution distribution = new FDistribution(
        degreesOfFreedomOfTreatment, degreesOfFreedomOfError);
    pValue = 1.0 - distribution.cumulativeProbability(anovaStatistics);
  }
  catch (MathIllegalArgumentException ex) {
    logger.warning("Error during F-distribution calculation: " + ex.getMessage());
  }

  return pValue;
}

Example 5

Source File: AnovaTask.java From mzmine3 with GNU General Public License v2.0

4 votes

@Nullable
private Double oneWayAnova(@Nonnull double[][] intensityGroups) {

  int numGroups = intensityGroups.length;
  long numIntensities = Arrays.stream(intensityGroups).flatMapToDouble(Arrays::stream).count();

  double[] groupMeans = Arrays.stream(intensityGroups)
      .mapToDouble(intensities -> Arrays.stream(intensities).average().orElse(0.0)).toArray();

  double overallMean =
      Arrays.stream(intensityGroups).flatMapToDouble(Arrays::stream).average().orElse(0.0);

  double sumOfSquaresOfError = IntStream.range(0, intensityGroups.length).mapToDouble(
      i -> Arrays.stream(intensityGroups[i]).map(x -> x - groupMeans[i]).map(x -> x * x).sum())
      .sum();

  double sumOfSquaresOfTreatment =
      (numGroups - 1) * Arrays.stream(groupMeans).map(x -> x - overallMean).map(x -> x * x).sum();

  long degreesOfFreedomOfTreatment = numGroups - 1;
  long degreesOfFreedomOfError = numIntensities - numGroups;

  if (degreesOfFreedomOfTreatment <= 0 || degreesOfFreedomOfError <= 0) {
    return null;
  }

  double meanSquareOfTreatment = sumOfSquaresOfTreatment / degreesOfFreedomOfTreatment;
  double meanSquareOfError = sumOfSquaresOfError / degreesOfFreedomOfError;

  if (meanSquareOfError == 0.0) {
    return null;
  }

  double anovaStatistics = meanSquareOfTreatment / meanSquareOfError;

  Double pValue = null;
  try {
    FDistribution distribution =
        new FDistribution(degreesOfFreedomOfTreatment, degreesOfFreedomOfError);
    pValue = 1.0 - distribution.cumulativeProbability(anovaStatistics);
  } catch (MathIllegalArgumentException ex) {
    logger.warning("Error during F-distribution calculation: " + ex.getMessage());
  }

  return pValue;
}

Example 6