Companion
Functions
Computes the AIC based on the sample size sampleSize, the number of parameters estimated for the model numParameters, and the maximized value lnMax of the log-likelihood function of the model. Implementation based on Vose
Computes the Anderson-Darling test statistic. No adjustments for parameter estimation are performed.
Computes the auto-correlations for k = 1 to and including maxLag The returned array is zero based indexed such that, ac0 is the lag-1 lag-0 is not returned because it is always 1.0
Computes the BIC based on the sample size sampleSize, the number of parameters estimated for the model numParameters, and the maximized value lnMax of the log-likelihood function of the model.
Computes the box plot summaries for the data within the map
Computes the chi-squared test statistic based on the observed counts and the expected counts. The expected counts must not contain a zero value. The size of the arrays must match.
Computes the chi-squared test statistic based on the supplied data and hypothesized distribution function, fn. The break points breakPoints are used to define the binning and tabulation of the counts for the data.
Computes the confidence intervals for the data in the map
Computes the covariance between the two arrays based on n = min(x.size, y.size) elements. There must be at least two elements in each array.
Assumes that the data is in each row of the matrix and that each row has the same number of elements. That is, the matrix must be rectangular.
Computes the Cramer-von Mises test statistic
Returns the rank of each element in the supplied data as a separate array of ranks. If ranks is the returned array, then ranks0 indicates the rank of element 0 in the data array. In dense ranking, items that compare equally receive the same ranking number, and the next items receive the immediately following ranking number. This is called dense ranking
Computes the proportion of the observations that are less than or equal to the supplied value of x. If the array is empty, then 0.0 is returned.
Computes the empirical quantiles based on the empirical probabilities for a data set of size n using the supplied quantileFunction inverse CDF. The type represents the continuity type as per the empiricalProbabilities() function.
Estimate the sample size for a proportion based on a normal approximation
Estimate the sample size based on a normal approximation
Estimate the sample size based on iterating the half-width equation based on the Student-T distribution: hw = t(1-alpha/2, n-1)*s/sqrt(n) <= epsilon
Returns the rank of each element in the supplied data as a separate array of ranks. If ranks is the returned array, then ranks0 indicates the rank of element 0 in the data array. Ties are handled by assigning the mean of the ranks that would have been given otherwise, so that the sum of the ranks is preserved. This is called fractional ranking
Computes the G test statistic based on the observed counts and the expected counts. The expected counts must not contain a zero value. The size of the arrays must match.
Computes the Hannan-Quinn criterion based on the sample size sampleSize, the number of parameters estimated for the model numParameters, and the maximized value lnMax of the log-likelihood function of the model. Implementation based on Vose
Computes the K-S test statistic for testing if the data comes from the supplied distribution.
Returns the median of the data. The array is sorted
Computes initialization bias (negative) test statistic based on algorithm on page 2580 Chapter 102 Nelson Handbook of Industrial Engineering, Quantitative Methods in Simulation
Uses the batch means array from the BatchStatistic to compute the positive bias test statistic
Returns the rank of each element in the supplied data as a separate array of ranks. If ranks is the returned array, then ranks0 indicates the rank of element 0 in the data array. Each element gets a unique rank based on the sorted order of the data array. Ties are handled arbitrarily based on the underlying sorting mechanism, which seems to be predicated on the "first" ranking method for the R rank() function.
Gets an array of the partial sum process for the provided data Based on page 2575 Chapter 102 Nelson Handbook of Industrial Engineering, Quantitative Methods in Simulation for producing a partial sum plot The batch means array is used as the data
Gets an array of the partial sum process for the provided data Based on page 2575 Chapter 102 Nelson Handbook of Industrial Engineering, Quantitative Methods in Simulation for producing a partial sum plot
Computes the Pearson correlation between the elements of the array based on n = min(x.size, y.size) elements. There must be at least two elements in each array.
As per Apache Math commons definition
Computes initialization bias (positive) test statistic based on algorithm on page 2580 Chapter 102 Nelson Handbook of Industrial Engineering, Quantitative Methods in Simulation
Uses the batch means array from the BatchStatistic to compute the positive bias test statistic
Uses definition 7, as per R definitions
Uses definition 7, as per R definitions
Uses definition 7, as per R definitions
Uses definition 7, as per R definitions
Computes the ranks for the data array based on the supplied ranking method.
Computes the statistical summaries for the data within the map
Computes the Watson test statistic