org.apache.commons.math.stat.descriptive.summary.SumOfSquares Java Examples

/**
 * Construct a MultivariateSummaryStatistics instance
 * @param k dimension of the data
 * @param isCovarianceBiasCorrected if true, the unbiased sample
 * covariance is computed, otherwise the biased population covariance
 * is computed
 */
public MultivariateSummaryStatistics(int k, boolean isCovarianceBiasCorrected) {
    this.k = k;

    sumImpl     = new StorelessUnivariateStatistic[k];
    sumSqImpl   = new StorelessUnivariateStatistic[k];
    minImpl     = new StorelessUnivariateStatistic[k];
    maxImpl     = new StorelessUnivariateStatistic[k];
    sumLogImpl  = new StorelessUnivariateStatistic[k];
    geoMeanImpl = new StorelessUnivariateStatistic[k];
    meanImpl    = new StorelessUnivariateStatistic[k];

    for (int i = 0; i < k; ++i) {
        sumImpl[i]     = new Sum();
        sumSqImpl[i]   = new SumOfSquares();
        minImpl[i]     = new Min();
        maxImpl[i]     = new Max();
        sumLogImpl[i]  = new SumOfLogs();
        geoMeanImpl[i] = new GeometricMean();
        meanImpl[i]    = new Mean();
    }

    covarianceImpl =
        new VectorialCovariance(k, isCovarianceBiasCorrected);

}
 

/**
 * Construct a MultivariateSummaryStatistics instance
 * @param k dimension of the data
 * @param isCovarianceBiasCorrected if true, the unbiased sample
 * covariance is computed, otherwise the biased population covariance
 * is computed
 */
public MultivariateSummaryStatistics(int k, boolean isCovarianceBiasCorrected) {
    this.k = k;

    sumImpl     = new StorelessUnivariateStatistic[k];
    sumSqImpl   = new StorelessUnivariateStatistic[k];
    minImpl     = new StorelessUnivariateStatistic[k];
    maxImpl     = new StorelessUnivariateStatistic[k];
    sumLogImpl  = new StorelessUnivariateStatistic[k];
    geoMeanImpl = new StorelessUnivariateStatistic[k];
    meanImpl    = new StorelessUnivariateStatistic[k];

    for (int i = 0; i < k; ++i) {
        sumImpl[i]     = new Sum();
        sumSqImpl[i]   = new SumOfSquares();
        minImpl[i]     = new Min();
        maxImpl[i]     = new Max();
        sumLogImpl[i]  = new SumOfLogs();
        geoMeanImpl[i] = new GeometricMean();
        meanImpl[i]    = new Mean();
    }

    covarianceImpl =
        new VectorialCovariance(k, isCovarianceBiasCorrected);

}
 

/**
 * Construct a MultivariateSummaryStatistics instance
 * @param k dimension of the data
 * @param isCovarianceBiasCorrected if true, the unbiased sample
 * covariance is computed, otherwise the biased population covariance
 * is computed
 */
public MultivariateSummaryStatistics(int k, boolean isCovarianceBiasCorrected) {
    this.k = k;

    sumImpl     = new StorelessUnivariateStatistic[k];
    sumSqImpl   = new StorelessUnivariateStatistic[k];
    minImpl     = new StorelessUnivariateStatistic[k];
    maxImpl     = new StorelessUnivariateStatistic[k];
    sumLogImpl  = new StorelessUnivariateStatistic[k];
    geoMeanImpl = new StorelessUnivariateStatistic[k];
    meanImpl    = new StorelessUnivariateStatistic[k];

    for (int i = 0; i < k; ++i) {
        sumImpl[i]     = new Sum();
        sumSqImpl[i]   = new SumOfSquares();
        minImpl[i]     = new Min();
        maxImpl[i]     = new Max();
        sumLogImpl[i]  = new SumOfLogs();
        geoMeanImpl[i] = new GeometricMean();
        meanImpl[i]    = new Mean();
    }

    covarianceImpl =
        new VectorialCovariance(k, isCovarianceBiasCorrected);

}
 

/**
 * Construct a MultivariateSummaryStatistics instance
 * @param k dimension of the data
 * @param isCovarianceBiasCorrected if true, the unbiased sample
 * covariance is computed, otherwise the biased population covariance
 * is computed
 */
public MultivariateSummaryStatistics(int k, boolean isCovarianceBiasCorrected) {
    this.k = k;

    sumImpl     = new StorelessUnivariateStatistic[k];
    sumSqImpl   = new StorelessUnivariateStatistic[k];
    minImpl     = new StorelessUnivariateStatistic[k];
    maxImpl     = new StorelessUnivariateStatistic[k];
    sumLogImpl  = new StorelessUnivariateStatistic[k];
    geoMeanImpl = new StorelessUnivariateStatistic[k];
    meanImpl    = new StorelessUnivariateStatistic[k];

    for (int i = 0; i < k; ++i) {
        sumImpl[i]     = new Sum();
        sumSqImpl[i]   = new SumOfSquares();
        minImpl[i]     = new Min();
        maxImpl[i]     = new Max();
        sumLogImpl[i]  = new SumOfLogs();
        geoMeanImpl[i] = new GeometricMean();
        meanImpl[i]    = new Mean();
    }

    covarianceImpl =
        new VectorialCovariance(k, isCovarianceBiasCorrected);

}
 

/**
 * Construct a MultivariateSummaryStatistics instance
 * @param k dimension of the data
 * @param isCovarianceBiasCorrected if true, the unbiased sample
 * covariance is computed, otherwise the biased population covariance
 * is computed
 */
public MultivariateSummaryStatistics(int k, boolean isCovarianceBiasCorrected) {
    this.k = k;

    sumImpl     = new StorelessUnivariateStatistic[k];
    sumSqImpl   = new StorelessUnivariateStatistic[k];
    minImpl     = new StorelessUnivariateStatistic[k];
    maxImpl     = new StorelessUnivariateStatistic[k];
    sumLogImpl  = new StorelessUnivariateStatistic[k];
    geoMeanImpl = new StorelessUnivariateStatistic[k];
    meanImpl    = new StorelessUnivariateStatistic[k];

    for (int i = 0; i < k; ++i) {
        sumImpl[i]     = new Sum();
        sumSqImpl[i]   = new SumOfSquares();
        minImpl[i]     = new Min();
        maxImpl[i]     = new Max();
        sumLogImpl[i]  = new SumOfLogs();
        geoMeanImpl[i] = new GeometricMean();
        meanImpl[i]    = new Mean();
    }

    covarianceImpl =
        new VectorialCovariance(k, isCovarianceBiasCorrected);

}
 

/**
 * Construct a MultivariateSummaryStatistics instance
 * @param k dimension of the data
 * @param isCovarianceBiasCorrected if true, the unbiased sample
 * covariance is computed, otherwise the biased population covariance
 * is computed
 */
public MultivariateSummaryStatistics(int k, boolean isCovarianceBiasCorrected) {
    this.k = k;

    sumImpl     = new StorelessUnivariateStatistic[k];
    sumSqImpl   = new StorelessUnivariateStatistic[k];
    minImpl     = new StorelessUnivariateStatistic[k];
    maxImpl     = new StorelessUnivariateStatistic[k];
    sumLogImpl  = new StorelessUnivariateStatistic[k];
    geoMeanImpl = new StorelessUnivariateStatistic[k];
    meanImpl    = new StorelessUnivariateStatistic[k];

    for (int i = 0; i < k; ++i) {
        sumImpl[i]     = new Sum();
        sumSqImpl[i]   = new SumOfSquares();
        minImpl[i]     = new Min();
        maxImpl[i]     = new Max();
        sumLogImpl[i]  = new SumOfLogs();
        geoMeanImpl[i] = new GeometricMean();
        meanImpl[i]    = new Mean();
    }

    covarianceImpl =
        new VectorialCovariance(k, isCovarianceBiasCorrected);

}
 

/**
 * Construct a MultivariateSummaryStatistics instance
 * @param k dimension of the data
 * @param isCovarianceBiasCorrected if true, the unbiased sample
 * covariance is computed, otherwise the biased population covariance
 * is computed
 */
public MultivariateSummaryStatistics(int k, boolean isCovarianceBiasCorrected) {
    this.k = k;

    sumImpl     = new StorelessUnivariateStatistic[k];
    sumSqImpl   = new StorelessUnivariateStatistic[k];
    minImpl     = new StorelessUnivariateStatistic[k];
    maxImpl     = new StorelessUnivariateStatistic[k];
    sumLogImpl  = new StorelessUnivariateStatistic[k];
    geoMeanImpl = new StorelessUnivariateStatistic[k];
    meanImpl    = new StorelessUnivariateStatistic[k];

    for (int i = 0; i < k; ++i) {
        sumImpl[i]     = new Sum();
        sumSqImpl[i]   = new SumOfSquares();
        minImpl[i]     = new Min();
        maxImpl[i]     = new Max();
        sumLogImpl[i]  = new SumOfLogs();
        geoMeanImpl[i] = new GeometricMean();
        meanImpl[i]    = new Mean();
    }

    covarianceImpl =
        new VectorialCovariance(k, isCovarianceBiasCorrected);

}
 

/**
 * Construct a MultivariateSummaryStatistics instance
 * @param k dimension of the data
 * @param isCovarianceBiasCorrected if true, the unbiased sample
 * covariance is computed, otherwise the biased population covariance
 * is computed
 */
public MultivariateSummaryStatistics(int k, boolean isCovarianceBiasCorrected) {
    this.k = k;

    sumImpl     = new StorelessUnivariateStatistic[k];
    sumSqImpl   = new StorelessUnivariateStatistic[k];
    minImpl     = new StorelessUnivariateStatistic[k];
    maxImpl     = new StorelessUnivariateStatistic[k];
    sumLogImpl  = new StorelessUnivariateStatistic[k];
    geoMeanImpl = new StorelessUnivariateStatistic[k];
    meanImpl    = new StorelessUnivariateStatistic[k];

    for (int i = 0; i < k; ++i) {
        sumImpl[i]     = new Sum();
        sumSqImpl[i]   = new SumOfSquares();
        minImpl[i]     = new Min();
        maxImpl[i]     = new Max();
        sumLogImpl[i]  = new SumOfLogs();
        geoMeanImpl[i] = new GeometricMean();
        meanImpl[i]    = new Mean();
    }

    covarianceImpl =
        new VectorialCovariance(k, isCovarianceBiasCorrected);

}
 

/**
 * Construct a MultivariateSummaryStatistics instance
 * @param k dimension of the data
 * @param isCovarianceBiasCorrected if true, the unbiased sample
 * covariance is computed, otherwise the biased population covariance
 * is computed
 */
public MultivariateSummaryStatistics(int k, boolean isCovarianceBiasCorrected) {
    this.k = k;

    sumImpl     = new StorelessUnivariateStatistic[k];
    sumSqImpl   = new StorelessUnivariateStatistic[k];
    minImpl     = new StorelessUnivariateStatistic[k];
    maxImpl     = new StorelessUnivariateStatistic[k];
    sumLogImpl  = new StorelessUnivariateStatistic[k];
    geoMeanImpl = new StorelessUnivariateStatistic[k];
    meanImpl    = new StorelessUnivariateStatistic[k];

    for (int i = 0; i < k; ++i) {
        sumImpl[i]     = new Sum();
        sumSqImpl[i]   = new SumOfSquares();
        minImpl[i]     = new Min();
        maxImpl[i]     = new Max();
        sumLogImpl[i]  = new SumOfLogs();
        geoMeanImpl[i] = new GeometricMean();
        meanImpl[i]    = new Mean();
    }

    covarianceImpl =
        new VectorialCovariance(k, isCovarianceBiasCorrected);

}
 

/**
 * Construct a MultivariateSummaryStatistics instance
 * @param k dimension of the data
 * @param isCovarianceBiasCorrected if true, the unbiased sample
 * covariance is computed, otherwise the biased population covariance
 * is computed
 */
public MultivariateSummaryStatistics(int k, boolean isCovarianceBiasCorrected) {
    this.k = k;

    sumImpl     = new StorelessUnivariateStatistic[k];
    sumSqImpl   = new StorelessUnivariateStatistic[k];
    minImpl     = new StorelessUnivariateStatistic[k];
    maxImpl     = new StorelessUnivariateStatistic[k];
    sumLogImpl  = new StorelessUnivariateStatistic[k];
    geoMeanImpl = new StorelessUnivariateStatistic[k];
    meanImpl    = new StorelessUnivariateStatistic[k];

    for (int i = 0; i < k; ++i) {
        sumImpl[i]     = new Sum();
        sumSqImpl[i]   = new SumOfSquares();
        minImpl[i]     = new Min();
        maxImpl[i]     = new Max();
        sumLogImpl[i]  = new SumOfLogs();
        geoMeanImpl[i] = new GeometricMean();
        meanImpl[i]    = new Mean();
    }

    covarianceImpl =
        new VectorialCovariance(k, isCovarianceBiasCorrected);

}
 

/**
 * Construct a MultivariateSummaryStatistics instance
 * @param k dimension of the data
 * @param isCovarianceBiasCorrected if true, the unbiased sample
 * covariance is computed, otherwise the biased population covariance
 * is computed
 */
public MultivariateSummaryStatistics(int k, boolean isCovarianceBiasCorrected) {
    this.k = k;

    sumImpl     = new StorelessUnivariateStatistic[k];
    sumSqImpl   = new StorelessUnivariateStatistic[k];
    minImpl     = new StorelessUnivariateStatistic[k];
    maxImpl     = new StorelessUnivariateStatistic[k];
    sumLogImpl  = new StorelessUnivariateStatistic[k];
    geoMeanImpl = new StorelessUnivariateStatistic[k];
    meanImpl    = new StorelessUnivariateStatistic[k];

    for (int i = 0; i < k; ++i) {
        sumImpl[i]     = new Sum();
        sumSqImpl[i]   = new SumOfSquares();
        minImpl[i]     = new Min();
        maxImpl[i]     = new Max();
        sumLogImpl[i]  = new SumOfLogs();
        geoMeanImpl[i] = new GeometricMean();
        meanImpl[i]    = new Mean();
    }

    covarianceImpl =
        new VectorialCovariance(k, isCovarianceBiasCorrected);

}
 

/**
 * Construct a MultivariateSummaryStatistics instance
 * @param k dimension of the data
 * @param isCovarianceBiasCorrected if true, the unbiased sample
 * covariance is computed, otherwise the biased population covariance
 * is computed
 */
public MultivariateSummaryStatistics(int k, boolean isCovarianceBiasCorrected) {
    this.k = k;

    sumImpl     = new StorelessUnivariateStatistic[k];
    sumSqImpl   = new StorelessUnivariateStatistic[k];
    minImpl     = new StorelessUnivariateStatistic[k];
    maxImpl     = new StorelessUnivariateStatistic[k];
    sumLogImpl  = new StorelessUnivariateStatistic[k];
    geoMeanImpl = new StorelessUnivariateStatistic[k];
    meanImpl    = new StorelessUnivariateStatistic[k];

    for (int i = 0; i < k; ++i) {
        sumImpl[i]     = new Sum();
        sumSqImpl[i]   = new SumOfSquares();
        minImpl[i]     = new Min();
        maxImpl[i]     = new Max();
        sumLogImpl[i]  = new SumOfLogs();
        geoMeanImpl[i] = new GeometricMean();
        meanImpl[i]    = new Mean();
    }

    covarianceImpl =
        new VectorialCovariance(k, isCovarianceBiasCorrected);

}
 

/**
 * Construct a MultivariateSummaryStatistics instance
 * @param k dimension of the data
 * @param isCovarianceBiasCorrected if true, the unbiased sample
 * covariance is computed, otherwise the biased population covariance
 * is computed
 */
public MultivariateSummaryStatistics(int k, boolean isCovarianceBiasCorrected) {
    this.k = k;

    sumImpl     = new StorelessUnivariateStatistic[k];
    sumSqImpl   = new StorelessUnivariateStatistic[k];
    minImpl     = new StorelessUnivariateStatistic[k];
    maxImpl     = new StorelessUnivariateStatistic[k];
    sumLogImpl  = new StorelessUnivariateStatistic[k];
    geoMeanImpl = new StorelessUnivariateStatistic[k];
    meanImpl    = new StorelessUnivariateStatistic[k];

    for (int i = 0; i < k; ++i) {
        sumImpl[i]     = new Sum();
        sumSqImpl[i]   = new SumOfSquares();
        minImpl[i]     = new Min();
        maxImpl[i]     = new Max();
        sumLogImpl[i]  = new SumOfLogs();
        geoMeanImpl[i] = new GeometricMean();
        meanImpl[i]    = new Mean();
    }

    covarianceImpl =
        new VectorialCovariance(k, isCovarianceBiasCorrected);

}
 

/**
 * Construct a MultivariateSummaryStatistics instance
 * @param k dimension of the data
 * @param isCovarianceBiasCorrected if true, the unbiased sample
 * covariance is computed, otherwise the biased population covariance
 * is computed
 */
public MultivariateSummaryStatistics(int k, boolean isCovarianceBiasCorrected) {
    this.k = k;

    sumImpl     = new StorelessUnivariateStatistic[k];
    sumSqImpl   = new StorelessUnivariateStatistic[k];
    minImpl     = new StorelessUnivariateStatistic[k];
    maxImpl     = new StorelessUnivariateStatistic[k];
    sumLogImpl  = new StorelessUnivariateStatistic[k];
    geoMeanImpl = new StorelessUnivariateStatistic[k];
    meanImpl    = new StorelessUnivariateStatistic[k];

    for (int i = 0; i < k; ++i) {
        sumImpl[i]     = new Sum();
        sumSqImpl[i]   = new SumOfSquares();
        minImpl[i]     = new Min();
        maxImpl[i]     = new Max();
        sumLogImpl[i]  = new SumOfLogs();
        geoMeanImpl[i] = new GeometricMean();
        meanImpl[i]    = new Mean();
    }

    covarianceImpl =
        new VectorialCovariance(k, isCovarianceBiasCorrected);

}
 

/**
 * Construct a MultivariateSummaryStatistics instance
 * @param k dimension of the data
 * @param isCovarianceBiasCorrected if true, the unbiased sample
 * covariance is computed, otherwise the biased population covariance
 * is computed
 */
public MultivariateSummaryStatistics(int k, boolean isCovarianceBiasCorrected) {
    this.k = k;

    sumImpl     = new StorelessUnivariateStatistic[k];
    sumSqImpl   = new StorelessUnivariateStatistic[k];
    minImpl     = new StorelessUnivariateStatistic[k];
    maxImpl     = new StorelessUnivariateStatistic[k];
    sumLogImpl  = new StorelessUnivariateStatistic[k];
    geoMeanImpl = new StorelessUnivariateStatistic[k];
    meanImpl    = new StorelessUnivariateStatistic[k];

    for (int i = 0; i < k; ++i) {
        sumImpl[i]     = new Sum();
        sumSqImpl[i]   = new SumOfSquares();
        minImpl[i]     = new Min();
        maxImpl[i]     = new Max();
        sumLogImpl[i]  = new SumOfLogs();
        geoMeanImpl[i] = new GeometricMean();
        meanImpl[i]    = new Mean();
    }

    covarianceImpl =
        new VectorialCovariance(k, isCovarianceBiasCorrected);

}
 

/**
 * Construct a MultivariateSummaryStatistics instance
 * @param k dimension of the data
 * @param isCovarianceBiasCorrected if true, the unbiased sample
 * covariance is computed, otherwise the biased population covariance
 * is computed
 */
public MultivariateSummaryStatistics(int k, boolean isCovarianceBiasCorrected) {
    this.k = k;

    sumImpl     = new StorelessUnivariateStatistic[k];
    sumSqImpl   = new StorelessUnivariateStatistic[k];
    minImpl     = new StorelessUnivariateStatistic[k];
    maxImpl     = new StorelessUnivariateStatistic[k];
    sumLogImpl  = new StorelessUnivariateStatistic[k];
    geoMeanImpl = new StorelessUnivariateStatistic[k];
    meanImpl    = new StorelessUnivariateStatistic[k];

    for (int i = 0; i < k; ++i) {
        sumImpl[i]     = new Sum();
        sumSqImpl[i]   = new SumOfSquares();
        minImpl[i]     = new Min();
        maxImpl[i]     = new Max();
        sumLogImpl[i]  = new SumOfLogs();
        geoMeanImpl[i] = new GeometricMean();
        meanImpl[i]    = new Mean();
    }

    covarianceImpl =
        new VectorialCovariance(k, isCovarianceBiasCorrected);

}
 

/**
 * Construct a MultivariateSummaryStatistics instance
 * @param k dimension of the data
 * @param isCovarianceBiasCorrected if true, the unbiased sample
 * covariance is computed, otherwise the biased population covariance
 * is computed
 */
public MultivariateSummaryStatistics(int k, boolean isCovarianceBiasCorrected) {
    this.k = k;

    sumImpl     = new StorelessUnivariateStatistic[k];
    sumSqImpl   = new StorelessUnivariateStatistic[k];
    minImpl     = new StorelessUnivariateStatistic[k];
    maxImpl     = new StorelessUnivariateStatistic[k];
    sumLogImpl  = new StorelessUnivariateStatistic[k];
    geoMeanImpl = new StorelessUnivariateStatistic[k];
    meanImpl    = new StorelessUnivariateStatistic[k];

    for (int i = 0; i < k; ++i) {
        sumImpl[i]     = new Sum();
        sumSqImpl[i]   = new SumOfSquares();
        minImpl[i]     = new Min();
        maxImpl[i]     = new Max();
        sumLogImpl[i]  = new SumOfLogs();
        geoMeanImpl[i] = new GeometricMean();
        meanImpl[i]    = new Mean();
    }

    covarianceImpl =
        new VectorialCovariance(k, isCovarianceBiasCorrected);

}
 

/**
 * Construct a SummaryStatistics
 */
public SummaryStatisticsImpl() {
    sum = new Sum();
    sumsq = new SumOfSquares();
    min = new Min();
    max = new Max();
    sumLog = new SumOfLogs();
    geoMean = new GeometricMean();
    secondMoment = new SecondMoment();
}
 

/**
 * Copies source to dest.
 * <p>Neither source nor dest can be null.</p>
 *
 * @param source SummaryStatistics to copy
 * @param dest SummaryStatistics to copy to
 * @throws NullArgumentException if either source or dest is null
 */
public static void copy(SummaryStatistics source, SummaryStatistics dest)
    throws NullArgumentException {
    MathUtils.checkNotNull(source);
    MathUtils.checkNotNull(dest);
    dest.maxImpl = source.maxImpl.copy();
    dest.meanImpl = source.meanImpl.copy();
    dest.minImpl = source.minImpl.copy();
    dest.sumImpl = source.sumImpl.copy();
    dest.varianceImpl = source.varianceImpl.copy();
    dest.sumLogImpl = source.sumLogImpl.copy();
    dest.sumsqImpl = source.sumsqImpl.copy();
    if (source.getGeoMeanImpl() instanceof GeometricMean) {
        // Keep geoMeanImpl, sumLogImpl in synch
        dest.geoMeanImpl = new GeometricMean((SumOfLogs) dest.sumLogImpl);
    } else {
        dest.geoMeanImpl = source.geoMeanImpl.copy();
    }
    SecondMoment.copy(source.secondMoment, dest.secondMoment);
    dest.n = source.n;

    // Make sure that if stat == statImpl in source, same
    // holds in dest; otherwise copy stat
    if (source.geoMean == source.geoMeanImpl) {
        dest.geoMean = (GeometricMean) dest.geoMeanImpl;
    } else {
        GeometricMean.copy(source.geoMean, dest.geoMean);
    }
    if (source.max == source.maxImpl) {
        dest.max = (Max) dest.maxImpl;
    } else {
        Max.copy(source.max, dest.max);
    }
    if (source.mean == source.meanImpl) {
        dest.mean = (Mean) dest.meanImpl;
    } else {
        Mean.copy(source.mean, dest.mean);
    }
    if (source.min == source.minImpl) {
        dest.min = (Min) dest.minImpl;
    } else {
        Min.copy(source.min, dest.min);
    }
    if (source.sum == source.sumImpl) {
        dest.sum = (Sum) dest.sumImpl;
    } else {
        Sum.copy(source.sum, dest.sum);
    }
    if (source.variance == source.varianceImpl) {
        dest.variance = (Variance) dest.varianceImpl;
    } else {
        Variance.copy(source.variance, dest.variance);
    }
    if (source.sumLog == source.sumLogImpl) {
        dest.sumLog = (SumOfLogs) dest.sumLogImpl;
    } else {
        SumOfLogs.copy(source.sumLog, dest.sumLog);
    }
    if (source.sumsq == source.sumsqImpl) {
        dest.sumsq = (SumOfSquares) dest.sumsqImpl;
    } else {
        SumOfSquares.copy(source.sumsq, dest.sumsq);
    }
}
 

/**
 * This method actually does the calculations (except P-value).
 *
 * @param categoryData <code>Collection</code> of <code>double[]</code>
 * arrays each containing data for one category
 * @return computed AnovaStats
 * @throws IllegalArgumentException if categoryData does not meet
 * preconditions specified in the interface definition
 * @throws MathException if an error occurs computing the Anova stats
 */
private AnovaStats anovaStats(Collection<double[]> categoryData)
    throws IllegalArgumentException, MathException {

    // check if we have enough categories
    if (categoryData.size() < 2) {
        throw MathRuntimeException.createIllegalArgumentException(
              LocalizedFormats.TWO_OR_MORE_CATEGORIES_REQUIRED,
              categoryData.size());
    }

    // check if each category has enough data and all is double[]
    for (double[] array : categoryData) {
        if (array.length <= 1) {
            throw MathRuntimeException.createIllegalArgumentException(
                  LocalizedFormats.TWO_OR_MORE_VALUES_IN_CATEGORY_REQUIRED,
                  array.length);
        }
    }

    int dfwg = 0;
    double sswg = 0;
    Sum totsum = new Sum();
    SumOfSquares totsumsq = new SumOfSquares();
    int totnum = 0;

    for (double[] data : categoryData) {

        Sum sum = new Sum();
        SumOfSquares sumsq = new SumOfSquares();
        int num = 0;

        for (int i = 0; i < data.length; i++) {
            double val = data[i];

            // within category
            num++;
            sum.increment(val);
            sumsq.increment(val);

            // for all categories
            totnum++;
            totsum.increment(val);
            totsumsq.increment(val);
        }
        dfwg += num - 1;
        double ss = sumsq.getResult() - sum.getResult() * sum.getResult() / num;
        sswg += ss;
    }
    double sst = totsumsq.getResult() - totsum.getResult() *
        totsum.getResult()/totnum;
    double ssbg = sst - sswg;
    int dfbg = categoryData.size() - 1;
    double msbg = ssbg/dfbg;
    double mswg = sswg/dfwg;
    double F = msbg/mswg;

    return new AnovaStats(dfbg, dfwg, F);
}
 

/**
 * This method actually does the calculations (except P-value).
 * 
 * @param categoryData <code>Collection</code> of <code>double[]</code>
 * arrays each containing data for one category
 * @return computed AnovaStats
 * @throws IllegalArgumentException if categoryData does not meet
 * preconditions specified in the interface definition
 * @throws MathException if an error occurs computing the Anova stats
 */
private AnovaStats anovaStats(Collection<double[]> categoryData)
    throws IllegalArgumentException, MathException {

    // check if we have enough categories
    if (categoryData.size() < 2) {
        throw MathRuntimeException.createIllegalArgumentException(
              "two or more categories required, got {0}",
              categoryData.size());
    }
    
    // check if each category has enough data and all is double[]
    for (double[] array : categoryData) {
        if (array.length <= 1) {
            throw MathRuntimeException.createIllegalArgumentException(
                  "two or more values required in each category, one has {0}",
                  array.length);
        }
    }

    int dfwg = 0;
    double sswg = 0;
    Sum totsum = new Sum();
    SumOfSquares totsumsq = new SumOfSquares();
    int totnum = 0;
    
    for (double[] data : categoryData) {

        Sum sum = new Sum();
        SumOfSquares sumsq = new SumOfSquares();
        int num = 0;

        for (int i = 0; i < data.length; i++) {
            double val = data[i];

            // within category
            num++;
            sum.increment(val);
            sumsq.increment(val);

            // for all categories
            totnum++;
            totsum.increment(val);
            totsumsq.increment(val);
        }
        dfwg += num - 1;
        double ss = sumsq.getResult() - sum.getResult() * sum.getResult() / num;
        sswg += ss;
    }
    double sst = totsumsq.getResult() - totsum.getResult() * 
        totsum.getResult()/totnum;
    double ssbg = sst - sswg;
    int dfbg = categoryData.size() - 1;
    double msbg = ssbg/dfbg;
    double mswg = sswg/dfwg;
    double F = msbg/mswg;

    return new AnovaStats(dfbg, dfwg, F);
}
 

/**
 * Copies source to dest.
 * <p>Neither source nor dest can be null.</p>
 * 
 * @param source SummaryStatistics to copy
 * @param dest SummaryStatistics to copy to
 * @throws NullPointerException if either source or dest is null
 */
public static void copy(SummaryStatistics source, SummaryStatistics dest) {
    dest.maxImpl = source.maxImpl.copy();
    dest.meanImpl = source.meanImpl.copy();
    dest.minImpl = source.minImpl.copy();
    dest.sumImpl = source.sumImpl.copy();
    dest.varianceImpl = source.varianceImpl.copy();
    dest.sumLogImpl = source.sumLogImpl.copy();
    dest.sumsqImpl = source.sumsqImpl.copy();
    if (source.getGeoMeanImpl() instanceof GeometricMean) {
        // Keep geoMeanImpl, sumLogImpl in synch
        dest.geoMeanImpl = new GeometricMean((SumOfLogs) dest.sumLogImpl);
    } else {
        dest.geoMeanImpl = source.geoMeanImpl.copy();
    }
    SecondMoment.copy(source.secondMoment, dest.secondMoment);
    dest.n = source.n;
    
    // Make sure that if stat == statImpl in source, same
    // holds in dest; otherwise copy stat
    if (source.geoMean == source.geoMeanImpl) {
        dest.geoMean = (GeometricMean) dest.geoMeanImpl;
    } else {
        GeometricMean.copy(source.geoMean, dest.geoMean);
    } 
    if (source.max == source.maxImpl) {
        dest.max = (Max) dest.maxImpl;
    } else {
        Max.copy(source.max, dest.max);
    } 
    if (source.mean == source.meanImpl) {
        dest.mean = (Mean) dest.meanImpl;
    } else {
        Mean.copy(source.mean, dest.mean);
    } 
    if (source.min == source.minImpl) {
        dest.min = (Min) dest.minImpl;
    } else {
        Min.copy(source.min, dest.min);
    } 
    if (source.sum == source.sumImpl) {
        dest.sum = (Sum) dest.sumImpl;
    } else {
        Sum.copy(source.sum, dest.sum);
    } 
    if (source.variance == source.varianceImpl) {
        dest.variance = (Variance) dest.varianceImpl;
    } else {
        Variance.copy(source.variance, dest.variance);
    } 
    if (source.sumLog == source.sumLogImpl) {
        dest.sumLog = (SumOfLogs) dest.sumLogImpl;
    } else {
        SumOfLogs.copy(source.sumLog, dest.sumLog);
    } 
    if (source.sumsq == source.sumsqImpl) {
        dest.sumsq = (SumOfSquares) dest.sumsqImpl;
    } else {
        SumOfSquares.copy(source.sumsq, dest.sumsq);
    } 
}
 

/**
 * Copies source to dest.
 * <p>Neither source nor dest can be null.</p>
 *
 * @param source SummaryStatistics to copy
 * @param dest SummaryStatistics to copy to
 * @throws NullPointerException if either source or dest is null
 */
public static void copy(SummaryStatistics source, SummaryStatistics dest) {
    dest.maxImpl = source.maxImpl.copy();
    dest.meanImpl = source.meanImpl.copy();
    dest.minImpl = source.minImpl.copy();
    dest.sumImpl = source.sumImpl.copy();
    dest.varianceImpl = source.varianceImpl.copy();
    dest.sumLogImpl = source.sumLogImpl.copy();
    dest.sumsqImpl = source.sumsqImpl.copy();
    if (source.getGeoMeanImpl() instanceof GeometricMean) {
        // Keep geoMeanImpl, sumLogImpl in synch
        dest.geoMeanImpl = new GeometricMean((SumOfLogs) dest.sumLogImpl);
    } else {
        dest.geoMeanImpl = source.geoMeanImpl.copy();
    }
    SecondMoment.copy(source.secondMoment, dest.secondMoment);
    dest.n = source.n;

    // Make sure that if stat == statImpl in source, same
    // holds in dest; otherwise copy stat
    if (source.geoMean == source.geoMeanImpl) {
        dest.geoMean = (GeometricMean) dest.geoMeanImpl;
    } else {
        GeometricMean.copy(source.geoMean, dest.geoMean);
    }
    if (source.max == source.maxImpl) {
        dest.max = (Max) dest.maxImpl;
    } else {
        Max.copy(source.max, dest.max);
    }
    if (source.mean == source.meanImpl) {
        dest.mean = (Mean) dest.meanImpl;
    } else {
        Mean.copy(source.mean, dest.mean);
    }
    if (source.min == source.minImpl) {
        dest.min = (Min) dest.minImpl;
    } else {
        Min.copy(source.min, dest.min);
    }
    if (source.sum == source.sumImpl) {
        dest.sum = (Sum) dest.sumImpl;
    } else {
        Sum.copy(source.sum, dest.sum);
    }
    if (source.variance == source.varianceImpl) {
        dest.variance = (Variance) dest.varianceImpl;
    } else {
        Variance.copy(source.variance, dest.variance);
    }
    if (source.sumLog == source.sumLogImpl) {
        dest.sumLog = (SumOfLogs) dest.sumLogImpl;
    } else {
        SumOfLogs.copy(source.sumLog, dest.sumLog);
    }
    if (source.sumsq == source.sumsqImpl) {
        dest.sumsq = (SumOfSquares) dest.sumsqImpl;
    } else {
        SumOfSquares.copy(source.sumsq, dest.sumsq);
    }
}
 

/**
 * This method actually does the calculations (except P-value).
 * 
 * @param categoryData <code>Collection</code> of <code>double[]</code>
 * arrays each containing data for one category
 * @return computed AnovaStats
 * @throws IllegalArgumentException if categoryData does not meet
 * preconditions specified in the interface definition
 * @throws MathException if an error occurs computing the Anova stats
 */
private AnovaStats anovaStats(Collection<double[]> categoryData)
    throws IllegalArgumentException, MathException {

    // check if we have enough categories
    if (categoryData.size() < 2) {
        throw MathRuntimeException.createIllegalArgumentException(
              "two or more categories required, got {0}",
              categoryData.size());
    }
    
    // check if each category has enough data and all is double[]
    for (double[] array : categoryData) {
        if (array.length <= 1) {
            throw MathRuntimeException.createIllegalArgumentException(
                  "two or more values required in each category, one has {0}",
                  array.length);
        }
    }

    int dfwg = 0;
    double sswg = 0;
    Sum totsum = new Sum();
    SumOfSquares totsumsq = new SumOfSquares();
    int totnum = 0;
    
    for (double[] data : categoryData) {

        Sum sum = new Sum();
        SumOfSquares sumsq = new SumOfSquares();
        int num = 0;

        for (int i = 0; i < data.length; i++) {
            double val = data[i];

            // within category
            num++;
            sum.increment(val);
            sumsq.increment(val);

            // for all categories
            totnum++;
            totsum.increment(val);
            totsumsq.increment(val);
        }
        dfwg += num - 1;
        double ss = sumsq.getResult() - sum.getResult() * sum.getResult() / num;
        sswg += ss;
    }
    double sst = totsumsq.getResult() - totsum.getResult() * 
        totsum.getResult()/totnum;
    double ssbg = sst - sswg;
    int dfbg = categoryData.size() - 1;
    double msbg = ssbg/dfbg;
    double mswg = sswg/dfwg;
    double F = msbg/mswg;

    return new AnovaStats(dfbg, dfwg, F);
}
 

/**
 * Copies source to dest.
 * <p>Neither source nor dest can be null.</p>
 * 
 * @param source SummaryStatistics to copy
 * @param dest SummaryStatistics to copy to
 * @throws NullPointerException if either source or dest is null
 */
public static void copy(SummaryStatistics source, SummaryStatistics dest) {
    dest.maxImpl = source.maxImpl.copy();
    dest.meanImpl = source.meanImpl.copy();
    dest.minImpl = source.minImpl.copy();
    dest.sumImpl = source.sumImpl.copy();
    dest.varianceImpl = source.varianceImpl.copy();
    dest.sumLogImpl = source.sumLogImpl.copy();
    dest.sumsqImpl = source.sumsqImpl.copy();
    if (source.getGeoMeanImpl() instanceof GeometricMean) {
        // Keep geoMeanImpl, sumLogImpl in synch
        dest.geoMeanImpl = new GeometricMean((SumOfLogs) dest.sumLogImpl);
    } else {
        dest.geoMeanImpl = source.geoMeanImpl.copy();
    }
    SecondMoment.copy(source.secondMoment, dest.secondMoment);
    dest.n = source.n;
    
    // Make sure that if stat == statImpl in source, same
    // holds in dest; otherwise copy stat
    if (source.geoMean == source.geoMeanImpl) {
        dest.geoMean = (GeometricMean) dest.geoMeanImpl;
    } else {
        GeometricMean.copy(source.geoMean, dest.geoMean);
    } 
    if (source.max == source.maxImpl) {
        dest.max = (Max) dest.maxImpl;
    } else {
        Max.copy(source.max, dest.max);
    } 
    if (source.mean == source.meanImpl) {
        dest.mean = (Mean) dest.meanImpl;
    } else {
        Mean.copy(source.mean, dest.mean);
    } 
    if (source.min == source.minImpl) {
        dest.min = (Min) dest.minImpl;
    } else {
        Min.copy(source.min, dest.min);
    } 
    if (source.sum == source.sumImpl) {
        dest.sum = (Sum) dest.sumImpl;
    } else {
        Sum.copy(source.sum, dest.sum);
    } 
    if (source.variance == source.varianceImpl) {
        dest.variance = (Variance) dest.varianceImpl;
    } else {
        Variance.copy(source.variance, dest.variance);
    } 
    if (source.sumLog == source.sumLogImpl) {
        dest.sumLog = (SumOfLogs) dest.sumLogImpl;
    } else {
        SumOfLogs.copy(source.sumLog, dest.sumLog);
    } 
    if (source.sumsq == source.sumsqImpl) {
        dest.sumsq = (SumOfSquares) dest.sumsqImpl;
    } else {
        SumOfSquares.copy(source.sumsq, dest.sumsq);
    } 
}
 

/**
 * This method actually does the calculations (except P-value).
 *
 * @param categoryData <code>Collection</code> of <code>double[]</code>
 * arrays each containing data for one category
 * @return computed AnovaStats
 * @throws IllegalArgumentException if categoryData does not meet
 * preconditions specified in the interface definition
 * @throws MathException if an error occurs computing the Anova stats
 */
private AnovaStats anovaStats(Collection<double[]> categoryData)
    throws IllegalArgumentException, MathException {

    // check if we have enough categories
    if (categoryData.size() < 2) {
        throw MathRuntimeException.createIllegalArgumentException(
              "two or more categories required, got {0}",
              categoryData.size());
    }

    // check if each category has enough data and all is double[]
    for (double[] array : categoryData) {
        if (array.length <= 1) {
            throw MathRuntimeException.createIllegalArgumentException(
                  "two or more values required in each category, one has {0}",
                  array.length);
        }
    }

    int dfwg = 0;
    double sswg = 0;
    Sum totsum = new Sum();
    SumOfSquares totsumsq = new SumOfSquares();
    int totnum = 0;

    for (double[] data : categoryData) {

        Sum sum = new Sum();
        SumOfSquares sumsq = new SumOfSquares();
        int num = 0;

        for (int i = 0; i < data.length; i++) {
            double val = data[i];

            // within category
            num++;
            sum.increment(val);
            sumsq.increment(val);

            // for all categories
            totnum++;
            totsum.increment(val);
            totsumsq.increment(val);
        }
        dfwg += num - 1;
        double ss = sumsq.getResult() - sum.getResult() * sum.getResult() / num;
        sswg += ss;
    }
    double sst = totsumsq.getResult() - totsum.getResult() *
        totsum.getResult()/totnum;
    double ssbg = sst - sswg;
    int dfbg = categoryData.size() - 1;
    double msbg = ssbg/dfbg;
    double mswg = sswg/dfwg;
    double F = msbg/mswg;

    return new AnovaStats(dfbg, dfwg, F);
}
 

/**
 * This method actually does the calculations (except P-value).
 * 
 * @param categoryData <code>Collection</code> of <code>double[]</code>
 * arrays each containing data for one category
 * @return computed AnovaStats
 * @throws IllegalArgumentException if categoryData does not meet
 * preconditions specified in the interface definition
 * @throws MathException if an error occurs computing the Anova stats
 */
private AnovaStats anovaStats(Collection<double[]> categoryData)
    throws IllegalArgumentException, MathException {

    // check if we have enough categories
    if (categoryData.size() < 2) {
        throw MathRuntimeException.createIllegalArgumentException(
              "two or more categories required, got {0}",
              categoryData.size());
    }
    
    // check if each category has enough data and all is double[]
    for (double[] array : categoryData) {
        if (array.length <= 1) {
            throw MathRuntimeException.createIllegalArgumentException(
                  "two or more values required in each category, one has {0}",
                  array.length);
        }
    }

    int dfwg = 0;
    double sswg = 0;
    Sum totsum = new Sum();
    SumOfSquares totsumsq = new SumOfSquares();
    int totnum = 0;
    
    for (double[] data : categoryData) {

        Sum sum = new Sum();
        SumOfSquares sumsq = new SumOfSquares();
        int num = 0;

        for (int i = 0; i < data.length; i++) {
            double val = data[i];

            // within category
            num++;
            sum.increment(val);
            sumsq.increment(val);

            // for all categories
            totnum++;
            totsum.increment(val);
            totsumsq.increment(val);
        }
        dfwg += num - 1;
        double ss = sumsq.getResult() - sum.getResult() * sum.getResult() / num;
        sswg += ss;
    }
    double sst = totsumsq.getResult() - totsum.getResult() * 
        totsum.getResult()/totnum;
    double ssbg = sst - sswg;
    int dfbg = categoryData.size() - 1;
    double msbg = ssbg/dfbg;
    double mswg = sswg/dfwg;
    double F = msbg/mswg;

    return new AnovaStats(dfbg, dfwg, F);
}
 

/**
 * Copies source to dest.
 * <p>Neither source nor dest can be null.</p>
 * 
 * @param source SummaryStatistics to copy
 * @param dest SummaryStatistics to copy to
 * @throws NullPointerException if either source or dest is null
 */
public static void copy(SummaryStatistics source, SummaryStatistics dest) {
    dest.maxImpl = source.maxImpl.copy();
    dest.meanImpl = source.meanImpl.copy();
    dest.minImpl = source.minImpl.copy();
    dest.sumImpl = source.sumImpl.copy();
    dest.varianceImpl = source.varianceImpl.copy();
    dest.sumLogImpl = source.sumLogImpl.copy();
    dest.sumsqImpl = source.sumsqImpl.copy();
    if (source.getGeoMeanImpl() instanceof GeometricMean) {
        // Keep geoMeanImpl, sumLogImpl in synch
        dest.geoMeanImpl = new GeometricMean((SumOfLogs) dest.sumLogImpl);
    } else {
        dest.geoMeanImpl = source.geoMeanImpl.copy();
    }
    SecondMoment.copy(source.secondMoment, dest.secondMoment);
    dest.n = source.n;
    
    // Make sure that if stat == statImpl in source, same
    // holds in dest; otherwise copy stat
    if (source.geoMean == source.geoMeanImpl) {
        dest.geoMean = (GeometricMean) dest.geoMeanImpl;
    } else {
        GeometricMean.copy(source.geoMean, dest.geoMean);
    } 
    if (source.max == source.maxImpl) {
        dest.max = (Max) dest.maxImpl;
    } else {
        Max.copy(source.max, dest.max);
    } 
    if (source.mean == source.meanImpl) {
        dest.mean = (Mean) dest.meanImpl;
    } else {
        Mean.copy(source.mean, dest.mean);
    } 
    if (source.min == source.minImpl) {
        dest.min = (Min) dest.minImpl;
    } else {
        Min.copy(source.min, dest.min);
    } 
    if (source.sum == source.sumImpl) {
        dest.sum = (Sum) dest.sumImpl;
    } else {
        Sum.copy(source.sum, dest.sum);
    } 
    if (source.variance == source.varianceImpl) {
        dest.variance = (Variance) dest.varianceImpl;
    } else {
        Variance.copy(source.variance, dest.variance);
    } 
    if (source.sumLog == source.sumLogImpl) {
        dest.sumLog = (SumOfLogs) dest.sumLogImpl;
    } else {
        SumOfLogs.copy(source.sumLog, dest.sumLog);
    } 
    if (source.sumsq == source.sumsqImpl) {
        dest.sumsq = (SumOfSquares) dest.sumsqImpl;
    } else {
        SumOfSquares.copy(source.sumsq, dest.sumsq);
    } 
}
 

/**
 * Copies source to dest.
 * <p>Neither source nor dest can be null.</p>
 *
 * @param source SummaryStatistics to copy
 * @param dest SummaryStatistics to copy to
 * @throws NullArgumentException if either source or dest is null
 */
public static void copy(SummaryStatistics source, SummaryStatistics dest)
    throws NullArgumentException {
    MathUtils.checkNotNull(source);
    MathUtils.checkNotNull(dest);
    dest.maxImpl = source.maxImpl.copy();
    dest.minImpl = source.minImpl.copy();
    dest.sumImpl = source.sumImpl.copy();
    dest.sumLogImpl = source.sumLogImpl.copy();
    dest.sumsqImpl = source.sumsqImpl.copy();
    dest.secondMoment = source.secondMoment.copy();
    dest.n = source.n;

    // Keep commons-math supplied statistics with embedded moments in synch
    if (source.getVarianceImpl() instanceof Variance) {
        dest.varianceImpl = new Variance(dest.secondMoment);
    } else {
        dest.varianceImpl = source.varianceImpl.copy();
    }
    if (source.meanImpl instanceof Mean) {
        dest.meanImpl = new Mean(dest.secondMoment);
    } else {
        dest.meanImpl = source.meanImpl.copy();
    }
    if (source.getGeoMeanImpl() instanceof GeometricMean) {
        dest.geoMeanImpl = new GeometricMean((SumOfLogs) dest.sumLogImpl);
    } else {
        dest.geoMeanImpl = source.geoMeanImpl.copy();
    }

    // Make sure that if stat == statImpl in source, same
    // holds in dest; otherwise copy stat
    if (source.geoMean == source.geoMeanImpl) {
        dest.geoMean = (GeometricMean) dest.geoMeanImpl;
    } else {
        GeometricMean.copy(source.geoMean, dest.geoMean);
    }
    if (source.max == source.maxImpl) {
        dest.max = (Max) dest.maxImpl;
    } else {
        Max.copy(source.max, dest.max);
    }
    if (source.mean == source.meanImpl) {
        dest.mean = (Mean) dest.meanImpl;
    } else {
        Mean.copy(source.mean, dest.mean);
    }
    if (source.min == source.minImpl) {
        dest.min = (Min) dest.minImpl;
    } else {
        Min.copy(source.min, dest.min);
    }
    if (source.sum == source.sumImpl) {
        dest.sum = (Sum) dest.sumImpl;
    } else {
        Sum.copy(source.sum, dest.sum);
    }
    if (source.variance == source.varianceImpl) {
        dest.variance = (Variance) dest.varianceImpl;
    } else {
        Variance.copy(source.variance, dest.variance);
    }
    if (source.sumLog == source.sumLogImpl) {
        dest.sumLog = (SumOfLogs) dest.sumLogImpl;
    } else {
        SumOfLogs.copy(source.sumLog, dest.sumLog);
    }
    if (source.sumsq == source.sumsqImpl) {
        dest.sumsq = (SumOfSquares) dest.sumsqImpl;
    } else {
        SumOfSquares.copy(source.sumsq, dest.sumsq);
    }
}
 

/**
 * This method actually does the calculations (except P-value).
 *
 * @param categoryData <code>Collection</code> of <code>double[]</code>
 * arrays each containing data for one category
 * @return computed AnovaStats
 * @throws IllegalArgumentException if categoryData does not meet
 * preconditions specified in the interface definition
 * @throws MathException if an error occurs computing the Anova stats
 */
private AnovaStats anovaStats(Collection<double[]> categoryData)
    throws IllegalArgumentException, MathException {

    // check if we have enough categories
    if (categoryData.size() < 2) {
        throw MathRuntimeException.createIllegalArgumentException(
              "two or more categories required, got {0}",
              categoryData.size());
    }

    // check if each category has enough data and all is double[]
    for (double[] array : categoryData) {
        if (array.length <= 1) {
            throw MathRuntimeException.createIllegalArgumentException(
                  "two or more values required in each category, one has {0}",
                  array.length);
        }
    }

    int dfwg = 0;
    double sswg = 0;
    Sum totsum = new Sum();
    SumOfSquares totsumsq = new SumOfSquares();
    int totnum = 0;

    for (double[] data : categoryData) {

        Sum sum = new Sum();
        SumOfSquares sumsq = new SumOfSquares();
        int num = 0;

        for (int i = 0; i < data.length; i++) {
            double val = data[i];

            // within category
            num++;
            sum.increment(val);
            sumsq.increment(val);

            // for all categories
            totnum++;
            totsum.increment(val);
            totsumsq.increment(val);
        }
        dfwg += num - 1;
        double ss = sumsq.getResult() - sum.getResult() * sum.getResult() / num;
        sswg += ss;
    }
    double sst = totsumsq.getResult() - totsum.getResult() *
        totsum.getResult()/totnum;
    double ssbg = sst - sswg;
    int dfbg = categoryData.size() - 1;
    double msbg = ssbg/dfbg;
    double mswg = sswg/dfwg;
    double F = msbg/mswg;

    return new AnovaStats(dfbg, dfwg, F);
}